EP1130514A2 - Data migration method using storage area network - Google Patents
Data migration method using storage area network Download PDFInfo
- Publication number
- EP1130514A2 EP1130514A2 EP00119434A EP00119434A EP1130514A2 EP 1130514 A2 EP1130514 A2 EP 1130514A2 EP 00119434 A EP00119434 A EP 00119434A EP 00119434 A EP00119434 A EP 00119434A EP 1130514 A2 EP1130514 A2 EP 1130514A2
- Authority
- EP
- European Patent Office
- Prior art keywords
- storage system
- switch
- data
- port
- read
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 104
- 230000005012 migration Effects 0.000 title claims description 159
- 238000013508 migration Methods 0.000 title claims description 111
- 239000000835 fiber Substances 0.000 claims description 25
- 238000004891 communication Methods 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 16
- 230000010365 information processing Effects 0.000 claims 1
- 238000013500 data storage Methods 0.000 description 28
- 239000004744 fabric Substances 0.000 description 16
- 238000010586 diagram Methods 0.000 description 15
- 238000007726 management method Methods 0.000 description 14
- 238000012546 transfer Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 239000000725 suspension Substances 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013329 compounding Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1402—Saving, restoring, recovering or retrying
- G06F11/1446—Point-in-time backing up or restoration of persistent data
- G06F11/1458—Management of the backup or restore process
- G06F11/1464—Management of the backup or restore process for networked environments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0604—Improving or facilitating administration, e.g. storage management
- G06F3/0605—Improving or facilitating administration, e.g. storage management by facilitating the interaction with a user or administrator
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0646—Horizontal data movement in storage systems, i.e. moving data in between storage devices or systems
- G06F3/0647—Migration mechanisms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/067—Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
Definitions
- the present invention relates to a method of additionally attaching a new disk system (migration destination disk system) to a storage area network (hereafter referred to as SAN) and migrating data from an old disk system (migration source disk system), which is already connected to the SAN, to that new disk system and a device thereof.
- SAN storage area network
- Conventional computer systems are configured with a plurality of servers connected by a network such as a LAN and disk units are directly connected to each computer.
- the data inside each disk unit was managed by the directly connected server. In other words, data was managed in a distributed condition.
- the SAN which adopts a configuration in which a plurality of servers, a plurality of disk units, backup units, etc. are connected by a switch or hub has recently become a hot topic.
- Fiber channels are used to physically connect these units to a switch or hub.
- the advantages of configuring a system using a SAN are superior scalability and the realization of reduced management cost since unified management can be performed by integrating data distributed over a plurality of disk units. Consequently, a SAN is well suited to a large-scale system. Because many resources are interconnected with a SAN, the management of these resources is an important topic.
- the management of a logical volume (such as backup), as the management of a disk unit, is one example of that. At present, these management methods are being studied by the SNIA (Storage Networking Industry Association) and NSIC (National Storage Industry Consortium).
- US patent no. 5,680,640 discloses a system and method of migrating data from a first data storage system to a second data storage system.
- a summary of that is as follows.
- a first data storage system already connected to a host, network or other data processing system is detached from the aforementioned host and connected to a second data storage system.
- the aforementioned second data storage system is connected to the aforementioned host or aforementioned data processing system.
- the aforementioned second data storage system contains a data map or data table that indicates which data element is stored in the aforementioned second storage system and which data in the aforementioned first data storage system has been copied to the aforementioned second storage system.
- the aforementioned second data storage system judges whether that data has been stored in the aforementioned second data storage system or in the aforementioned first storage system. If the data has been stored in the aforementioned second data storage system, that data can be used by the host, etc. If the data is not stored in the aforementioned second data storage system, the aforementioned second data storage system issues a request to the aforementioned first data storage system, and that data can be used by the aforementioned host, etc. Then, the aforementioned second data storage system writes that data to its own system and updates the aforementioned data map or aforementioned data table.
- the aforementioned second data storage system When the aforementioned second data storage system is not busy, it scans the aforementioned data map or aforementioned data table, determines which data of the aforementioned first data storage system has not yet been copied into its own system, and executes the copying of that data and updating of the aforementioned data map or aforementioned data table.
- the procedure of detaching the aforementioned first data storage system from the aforementioned host, connecting it to the aforementioned second data storage system, and connecting the aforementioned second data storage system to the aforementioned host is necessary. Consequently, at least during the interval beginning when the aforementioned first data storage system is detached from the aforementioned host until the aforementioned second data storage system is connected to the aforementioned host and the aforementioned first storage system, the aforementioned host cannot issue I/O (Input/Output) requests. In addition, during that interval it is necessary to temporarily suspend applications or other programs on the aforementioned host that use the aforementioned first data storage system. To further suppress costs associated with data migration, it is necessary to further reduce the time when I/O requests cannot be issued and the time when applications are suspended.
- the object of the present invention is to provide data migration systems and methods that are well suited to a SAN environment.
- a host computer and first disk unit are each connected by means of a communication channel to a switch port, and it is assumed that the aforementioned first disk unit receives read/write requests from the aforementioned host computer via the aforementioned switch.
- Each port of the aforementioned switch is assigned a physical port ID and a logical port ID.
- the aforementioned switch is provided with a table that maintains the correspondence relation between the physical port ID and the logical port ID.
- the second disk unit is connected to a port of the aforementioned switch that is different from the port connected to the aforementioned host computer and the port connected to the aforementioned first disk unit.
- the aforementioned second disk unit obtains configuration information (the number of logical volumes and size of each logical volume, for example) of the aforementioned first disk unit. Then, the correspondence relation between the physical port ID and the logical port ID assigned to the port of the switch connected to the aforementioned first disk unit is exchanged with the correspondence relation between the physical port ID and the logical port ID assigned to the port of the switch connected to the aforementioned second disk unit. Concretely, the logical port ID assigned to the port of the switch connected to the aforementioned first disk unit and the logical port ID assigned to the port of the switch connected to the aforementioned second disk unit are exchanged.
- the aforementioned second disk unit After this port ID switching process is performed, the aforementioned second disk unit is configured with the logical volume that corresponds to the configuration information of the aforementioned first disk, and data in the aforementioned first disk unit is migrated to the aforementioned second disk unit. If there is a read or write request from the aforementioned host computer for data already migrated to the aforementioned second disk unit, that processing is performed for that data by the aforementioned second disk unit.
- FIG. 1 is a diagram that describes the configuration of the computer system in the first preferred embodiment of the present invention.
- FIG. 2 is a diagram that describes the configuration of the host.
- FIG. 3 is a diagram that describes the fabric configured with one switch.
- FIG. 4 is a diagram that describes the fabric configured with a plurality of switches.
- FIG. 5 is a diagram that describes the frame of the fiber channel.
- FIG. 6 indicate an example configuration of the port configuration table of the present invention: FIG. 6 (A) indicates an example configuration of the port configuration before port switching and FIG. 6 (B) indicates an example configuration of the port configuration after port switching.
- FIG. 7 indicates an example configuration of the old configuration information of the present invention.
- FIG. 8 indicates an example structure of the migration worktable of the present invention.
- FIG. 9 is a flowchart of the data migration procedure of the present invention.
- FIG. 10 is a flowchart of the port switching procedure of the present invention.
- FIG. 11 is a flowchart of the data migration procedure of the present invention.
- FIG. 12 is a diagram that describes the configuration of the computer system in the second preferred embodiment of the present invention.
- FIG. 13 is a diagram that describes the configuration of the computer system in the third preferred embodiment of the present invention.
- FIG. 14 indicates an example configuration of the port configuration table of the third preferred embodiment of the present invention.
- FIG. 15 indicates a flowchart of the data migration procedure of the third preferred embodiment of the present invention.
- FIG. 16 is a diagram that describes the configuration of the computer system in the fourth preferred embodiment of the present invention.
- FIG. 17 indicates an example configuration of the migrator of the present invention.
- FIG. 18 is a diagram that describes the configuration of the computer system in the fifth preferred embodiment of the present invention.
- FIG. 19 is a diagram that describes the configuration of the host in the fifth preferred embodiment of the present invention.
- FIG. 20 is a diagram that describes the correspondence between the physical port ID and logical port ID assigned to each port prior to the port switching procedure of the present invention.
- FIG. 21 is a diagram that describes the correspondence between the physical port ID and logical port ID assigned to each port after the port switching procedure of the present invention.
- FIG. 22 is an example configuration of the case where the management station of the present invention is connected to a LAN.
- preferred embodiments 1 through 5 propose data migration methods and devices, well suited to a SAN environment.
- a new disk system is connected to a switch that is already connected to a host and an old disk system, and using that switch, data on the old disk system is migrated to the new disk system. Therefore, because with the present preferred embodiment, there is no need to perform the task of detaching the connection between the host and old disk system and connecting a new disk system to the host and old disk system, and it is only required to connect a new disk system to the switch, compared to the data migration system and method disclosed in the aforementioned US patent no. 5,680,640, the work of adding a new disk system is reduced. Thus, the costs associated with data migration can also be suppressed. In addition, since it is unnecessary to provide a dedicated channel for data migration with the present preferred embodiment, hardware costs can also be reduced.
- FIG. 1 through FIG. 10 the present preferred embodiment will be described using FIG. 1 through FIG. 10.
- FIG. 1 is a diagram that describes the first preferred embodiment of a computer system to which the data migration system and method of the present invention is applied.
- Two hosts 101, old disk system 103 and new disk system 104 are connected with switch 102, and these form a SAN.
- Hosts 101, old disk system 103 and new disk system 104 are connected to switch 102 with fiber channel 105. Since the present invention performs data migration from old disk system 103 to new disk system 104, there is no limitation on the number of hosts.
- FIG. 5 indicates the frame format that is used with fiber channel 105. Between SOF (Start Of Frame) 501 that indicates the beginning of the frame and EOF (End Of Frame) 505 that indicates the end, frame header 502, data field 503 and CRC (Cyclic Redundancy Check) 504 are inserted into the frame.
- SOF Start Of Frame
- EOF End Of Frame
- CRC Cyclic Redundancy Check
- Frame header 502 includes frame control information and contains receive side address D_ID (Destination ID) 507, sending source address S_ID (Source ID) 508, R_CTL (Routing Control) 506 that controls the routing, TYPE 510 that indicates the data structure, F_CTL (Frame Control) 511 that controls the frame sequence and exchange, SEQ_ID (Sequence_ID) 512 that distinguishes between the sending source and receive side sequences, SEQ_CNT (Sequence count) 514 that indicates the count value of a number of frames of each sequence, and data field control information DF_CNTL (Data Field Control) 513. Details of the frame of fiber channel 105 are shown in ANSI X3.230 FC-PH (Fiber Channel Physical and Signaling Interface).
- FIG. 3 indicates a logical network connection configuration of the computer system shown in FIG. 1.
- fabric 301 is configured with one switch 102.
- Port 303 of switch 102 used in the connection of host 101 and the disk units, is called the F (Fabric) port.
- ports 302 of host 101 and the disk units are called N (Node) ports.
- fabric 301 can also be configured with a plurality of switches 102. The switch ports that connect to other switches are called the E (Expansion) ports 401.
- data transfers from host 101 to new disk system 104 are performed as follows.
- Host 101 stores its own port ID in S_ID 508, stores the port ID of a frame's sending destination in D_ID 507, and then sends the frame.
- switch 102 receives the frame, it examines the port ID which has been stored in D_ID 507 and sends the frame from the F_Port which matches that port ID to the N_Port of new disk system 104.
- S_ID 508 and D_ID are logical port IDs.
- Switch 102 includes switch controller 110, switch module 111 and port controller 112.
- Switch controller 110 performs control within switch 102 and includes CPU 114, memory controller 115, memory 116 and nonvolatile memory 117.
- CPU 114 using internal bus 113, performs the exchange of control information and data with each controller.
- nonvolatile memory 117 The read/write access to nonvolatile memory 117 is controlled by memory controller 115, and it stores such data as switch control program 119 which is necessary for the control of switch 102 and port configuration table 118 which is necessary during execution of that program.
- FIG. 6 indicates an example configuration of port configuration table 118.
- FIG. 6 (A) shows a port configuration table before port switching
- FIG. 6 (B) shows a port configuration table after port switching. The port switching procedure will be described later.
- Port configuration table 118 indicates the port configuration, and includes logical port ID 601 that indicates the logical port ID and physical port ID 602 that indicates the physical port ID. In addition, it may also include the rule of the transfer service class of the fiber channel and the port type such as loop.
- logical port ID_0 logical port ID
- logical port ID_1 old disk system 103 is connected to logical port ID_1
- a host 101 is connected to logical port ID_3.
- new disk system 104 is connected to logical port ID_2.
- the read/write access to memory 116 is controlled by memory controller 115.
- switch control program 119 is executed by CPU 114, that program is read from nonvolatile memory 117 and stored in memory 116. Further, at that time and as necessary, CPU 114 also reads port configuration table 118 from nonvolatile memory 117 and stores it in memory 116.
- Port controller 112 performs control of the data coding/compounding. Concretely, port controller 112 extracts serial data from a received fiber channel frame and converts it into parallel data, and extracts information necessary for switching such as the send destination ID from the frame and sends it to switch module 111. Also, port controller 112 performs the reverse procedure.
- Switch module 111 has a plurality of ports that are individually connected to a plurality of port controllers 112. Switch module 111 is connected to CPU 114 via internal bus 113 and is controlled by CPU 114. When switch module 111 receives data from port controller 112, in accordance with the send destination ID of that data, it switches a port to the output port and sends data. Switch module 111 may be made with a crossbar switch.
- Management station 150 connected to switch 102, sets the various parameters of switch 102, and performs control of the migration process which is the most characteristic function of the present preferred embodiment and information management. Further, management station 150 has the command to active the migration program (to be described later) on new disk system 104 and the command to acquire migration information (such as migrating, done, or error).
- management station 150 is directly connected to switch 102.
- the aforementioned settings may be implemented with the Web or other means, by connecting host 101, switch 102, old disk system 103, new disk system 104 and management station 150 to a LAN (Local Area Network).
- LAN Local Area Network
- old disk system 103 and new disk system 104 are assumed to have the same configuration, except for programs and information in memory.
- Old disk system 103 includes disk control unit 120 and disk unit 121.
- Disk unit 121 includes a plurality of disk drives 130. These disk drives 130 are connected to disk controller 124 with interface (I/F) 129 (fiber channel, SCSI, etc.). In the implementation of the present invention, the number of disk drives 130 is not restricted.
- Disk controller 120 includes CPU 122, memory controller 123, port controller 125, disk controller 124 and memory 126.
- CPU 122, memory controller 123, port controller 125 and disk controller 124 are connected with an internal bus.
- CPU 122 using the internal bus, performs the exchange of control information and data with these controllers.
- CPU 122 issues read and write commands to disk drive 130 that is necessary in the processing of commands sent from host 101 via switch 102.
- CPU 122 constructs the well-known RAID 0 ⁇ 5 configuration with a plurality of disk drives 130, and provides logical volumes for host 101.
- Port controller 125 is connected to port controller 112 of switch 102 by fiber channel 105 and has the same functions as port controller 112.
- Memory 126 is connected to memory controller 123 and stores disk unit control program 128 that controls the disk unit, data that are necessary during execution of said program, and configuration information 127. Configuration information 127 will be described later.
- Disk unit control program 128 is executed by CPU 122 and is a program that controls port controller 125 and disk controller 124, and processes read/write commands received from host 101.
- old configuration information 138 which has been read and transferred from configuration information 127 stored in memory 126 of old disk system 103, migration program 142 used during data migration, and migration worktable 143 that indicates the state of the data migration.
- FIG. 8 indicates an example structure of migration worktable 143.
- Migration worktable 143 includes volume number 801, slot number 802 and status 803 that indicates the status of said slot.
- FIG. 2 indicates the configuration of host 101.
- Host 101 includes CPU 201, memory controller 202, port controller 206, disk controller 204, disk drive 205 and memory 203.
- CPU 201 memory controller 202, port controller 206 and disk controller 204 are connected with internal bus 207.
- CPU 201 using internal bus 207, performs the exchange of control information and data with these controllers.
- Port controller 206 is connected to port controller 112 of switch 102 with fiber channel 105 and performs the exchange of commands and data with port controller 112.
- Disk drive 205 is connected to disk controller 204 and stores operating system 208, device driver 209 that controls hardware such as port controller 206, application program 210 and data that is necessary during execution of these programs.
- Memory 203 is connected to memory controller 202.
- operating system 208, disk controller 204, device driver 209, application program 210, etc. are executed by CPU 201, they are read from disk drive 205 and stored in memory 203.
- management station 150 First, an operator activates management station 150 and then inputs the port numbers of switch 102 that are connected to old disk system 103 and new disk system 104.
- any port ID may be assigned.
- the port ID assigned to the F_Port connected to new disk system 104 is appropriate.
- logical port ID_2 is assigned to new disk system 104.
- the operator After connecting new disk system 104, the operator activates migration program 142 on new disk system 104 with the aforementioned command from management station 150.
- the activated migration program 142 first obtains configuration information 127 from old disk system 103 (902).
- configuration information 127 includes old port ID 702, world wide name 703, fiber configuration information 704 and SCSI configuration information 705.
- Fiber configuration information 704 includes PLOGI payload 706 and PRLI payload 707.
- PLOGI payload 706 includes common service parameter 708 that are exchanged at the time of a fiber channel N_Port login (PLOGI), port name 709, node name 710 and class service parameter 711.
- Specified in common service parameter 708 are the fiber channel version information and functions such as the address specification method supported by said fiber channel device, the communication method, etc.
- Class service parameter 711 indicates the class support information, X_ID re-assignment, ACK capability, etc. Details of fiber channel parameters are described in the aforementioned ANSI X3.230 FC-PH.
- PRLI payload 707 includes service parameter 712.
- SCSI configuration information 705 includes inquiry data 703, disconnect/reconnect parameter 714, sense data 715 and mode select parameter 716.
- Inquiry data 713 indicates the type, vendor ID, product ID, etc. of the SCSI device.
- Disconnect/reconnect parameter 714 indicates the connection conditions. When an error occurs, sense data 715 is exchanged to investigate the state of the disk unit.
- Mode select parameter 716 performs the setting and modification of various parameters related to the physical attributes of the SCSI device, data format of the storage media, error recovery method and procedure, processing method of an I/O process, etc.
- inquiry data 713 and mode select parameter 716 the number of volumes and size of each volume (number of blocks) on old disk system 103 can be learned.
- a detailed description of the protocol for SCSI on fiber channel 105 is shown in ANSI X.269 Fiber Channel Protocol for SCSI.
- configuration information 127 can also exist as information in addition to that which can be acquired using protocols of the existing fiber channel, SCSI, etc. If that type of configuration information exists, the operator directly reads configuration information 127 from old disk system 103 and transfers it to new disk system 104. Reading and transferring are performed from an operation panel or by web access by means of HTTP.
- migration program 142 of new disk system 104 notifies switch 102 of that fact.
- switch control program 119 of switch 102 When switch control program 119 of switch 102 receives that notification, the port switching procedure is started.
- switch control program 119 of switch 102 notifies all hosts 101 using old disk system 103 that port switching has begun.
- Device driver 209 of host 101 that has received this notification queues an I/O process for old disk system 103 in memory 203 of host 101 (1001).
- switch control program 119 of switch 102 changes the correspondence relation between logical port ID 601 and physical port ID 602 of old disk system 103 and the correspondence relation between logical port ID 601 and physical port ID 602 of new disk system 104 of port configuration table 118 (1002).
- port configuration table 118 is rewritten as in FIG. 6 (B).
- port controller 112 of switch 102 performs the port switching procedure by manipulating S_ID 508 and D_ID 507.
- logical port ID 601 that corresponds to S_ID 508 of the frame is retrieved, and S_ID 508 of the frame is converted into physical port ID 602 that corresponds to the retrieved logical port ID 601.
- logical port ID 601 that corresponds to D_ID 507 of the frame is retrieved, and that D_ID 507 is converted into physical port ID 602 that corresponds to the retrieved logical port ID 601.
- CRC 504 that is appended to the frame is recalculated.
- switch 102 which will become the master (master switch) is determined.
- the master switch is switch 102 that is directly connected to new disk system 104.
- Switch control program 119 of the master switch notifies all hosts 101 that are using old disk system 103 and all switches except for the master switch in fabric 301 of the starting of port switching.
- the processing to be performed by device driver 209 of host 101 that has received such notification is the same as in the case where the fabric is configured from a single switch 102, except for notification to the master switch of the I/O suspension completion.
- switch control program 119 of the master switch changes the correspondence relation between logical port ID 601 and physical port ID 602 of old disk system 103 and the correspondence relation between logical port ID 601 and physical port ID 602 of new disk system 104 of port configuration table 118, and notifies all switches 102 except the master switch of that change. Based on such notification, all switches except for the master switch change their own port configuration table 118. Thereafter, the operation of each switch is the same as the operation of switch 102 in the case where the fabric is configured with a single switch 102. After port switching has been performed by all switches 102 in fabric 301, host 101 I/O is restarted.
- the data migration procedure is performed synchronously with the completion of the port switching procedure. This data migration procedure will be described using the flowchart of FIG. 11.
- migration program 142 constructs a volume in new disk system 104 that corresponds to the logical volume number and size of that volume in old disk system 103, and then initializes variables to be used and migration worktable 143 that was described with FIG. 8 (1101).
- Migration program 142 on new disk system 104 checks whether there is an I/O request from host 101 (1102).
- migration program 142 computes the address of the next data to migrate (1103).
- Data migration is performed for all the logical volumes of old disk system 103 in order of increasing volume number 801. Further, within each volume, data migration is performed beginning with the first block.
- Worktable 143 for migration shown in FIG. 8 indicates the next migration address in the volume number 801 cell of the first row. The initial value of the next migration address is the first block address of the smallest volume number 801.
- migration worktable 143 indicates the next migration slot in the slot number 802 cell of the first row. From the second row onward, the rows are arranged in order of increasing volume number 801 and slot number 802.
- migration program 142 transfers data of the next migration address obtained from migration worktable 143, it changes status 803 of that slot number to "Migrating" (1104).
- migration program 142 issues a request to read the slot size to old disk system 103 and acquires the corresponding data (1105).
- Migration program 142 writes the data obtained from old disk system 103 to a corresponding volume of new disk system 104 on disk drive 141, using disk controller 124 and via I/F 140 (1106).
- migration program 142 investigates whether the request is for a read or write access (1109).
- migration program 142 references migration worktable 143 and investigates whether migration of the requested data has been completed (1110).
- migration program 142 reads that data from disk drive 141 in new disk system 104 and sends it back to host 101 (1113, 1112).
- migration program 142 issues a read request to old disk system 103 via switch 102 and acquires said data.
- Migration program 142 sends back the data acquired from old disk system 103 to host 101 and also writes that data to the corresponding volume of new disk system 104 (1111, 1112).
- Migration program 142 receives data related to the write request from host 101 (1114).
- migration program 142 issues a read request in slot size units to old disk system 103 via switch 102 so as to include the data requested from host 101, and acquires the data.
- migration program 142 overwrites the data obtained from the migration source with the data received from host 101 and creates new slot data, it writes to the volume in new disk system 104 requested by host 101 (1115).
- migration program 142 registers said slot into migration worktable 143, and with status 803 set to "Done", the processing related to the write request from host 101 is finished (1107).
- the operator detaches old disk system 103 from the switch and terminates the migration procedure (905).
- the present preferred embodiment differs from preferred embodiment 1 in that in addition to the system configuration described with preferred embodiment 1, the old disk system and new disk system are directly connected with an interface (fiber channel or SCSI, for example).
- an interface fiber channel or SCSI, for example.
- data migration is performed using that interface, compared to preferred embodiment 1, high-speed data migration can be performed.
- it is necessary to provide an interface for data migration.
- there is no need to perform the task of connecting a new disk system to the host and old disk system by detaching the connection between the host and old disk system, and because it is only required to connect a new disk system to the switch and connect the old disk system and the new disk system with an interface, compared to the data migration system and method disclosed in the aforementioned US patent no. 5,680,640, the work of adding the new disk system is reduced.
- FIG. 12 is a diagram that describes the second preferred embodiment of a computer system that has adopted the data migration system and method of the present invention. As described above, each configuration element of the computer system is the same as each configuration element of FIG. 1, and therefore their descriptions are omitted.
- the data migration procedure flow is the same as that of preferred embodiment 1, which was described with FIG. 9.
- old disk system 1203 and new disk system 1204 are connected directly by a interface and data migration is performed using that interface, it is necessary to obtain the correspondence relation between the logical address and physical address in old disk system 1203 from old configuration information 1238. Below, only this point of difference will be described.
- steps 1105, 1113 and 1115 of FIG. 11 data is read from the old disk system via switch 102.
- migration program 1231 uses information that is included in old configuration information 1238, migrate program 1231 computes the physical address corresponding to the logical address of the data that should be read from old disk system 1203. Then, using I/F 1240, migration program 1231 issues directly a read request to disk drive 1230 of old disk system 1203 that corresponds to the computed physical address, and acquires that data. At this time, if that data has been distributed to a plurality of disk drives 1230 of old disk system 1203, or if stored in dispersed physical addresses, a plurality of read requests will be issued.
- old disk system 1203 and new disk system 1204 are connected directly with an interface, and data migration is performed using that interface without passing through switch 1202, compared to preferred embodiment 1, high-speed data migration can be performed. Further, since the data migration of the present preferred embodiment does not pass through switch 1202, the resource consumption of the switch can be suppressed.
- two hosts and two disk units are connected to switch 1202. However, because many hosts and disk units are connected in a SAN environment, those resources can be allocated to the data transfer between other hosts and other disk units. Therefore, by means of the present preferred embodiment, compared to preferred embodiment 1, the degradation of switch performance that accompanies data migration can be suppressed.
- the present preferred embodiment differs from preferred embodiment 1 in that the migration program is executed by a switch.
- the migration program is executed by a switch.
- FIG. 13 the configuration of the computer system of the present preferred embodiment will be described. However, a description of those configuration elements that are the same as configuration elements of FIG. 1 will be omitted.
- non-volatile memory 1317 in switch 1302 stores switch control program 1319 that is necessary for control of switch 1302, migration program 1342 that performs the migration procedure, port configuration table 1318 that is necessary during execution of these programs, old configuration information 1327 and migration worktable 1343.
- Disk unit control program 1339 is stored in memory 1337 in new disk system 1304, but the old configuration information, migration worktable, and migration program are not stored, though they are in preferred embodiment 1.
- FIG. 14 is an example configuration of port configuration table 1318 that indicates the port configuration.
- Port configuration table 1318 includes logical port ID 1401 that indicates the virtual port ID, physical port ID 1402 that indicates the physical port ID, and status 1403 that indicates the port status.
- migration program 1342 of switch 1302 reads configuration information 1327 from old disk system 1303 (1502).
- Configuration information 1327 is the same as that shown in FIG. 7.
- switch control program 1319 of switch 1302 starts the port switching procedure (1503).
- switch control program 1319 of switch 1302 sets port ID status 1403 of old disk system 1303 in port configuration table 1318 to "Migrating.”
- the frame for the port ID with "Migrating" status 1403 in port configuration table 1318 is not sent to the corresponding port, but instead is passed to migration program 1331 of switch 1302. In other words, access to old disk system 1303 is performed by migration program 1331 of switch 1302.
- switch control program 1319 of the master switch sets port ID status 1403 of old disk system 1303 in port configuration table 1318 to "Migrating.”
- the frame for the port ID with "Migrating" status 1403 in port configuration table 1318 is not sent to the corresponding port, but instead is passed to migration program 1331 of switch 1302.
- migration program 1342 of switch 1302 constructs a volume according to the logical volume number and size of said volume which are configured in old disk system 1303, and then initializes variables to be used and migration worktable 1332 that is shown with FIG. 8.
- the procedure thereafter is the same procedure as described in preferred embodiment 1, except that it is not performed by the migration program of the new disk system, but instead by migration program 1302 of switch 1302.
- switch control program 1319 of switch 1302 changes the status of new disk system 1304 in port configuration table 1318 to "Normal" (1505).
- the operator detaches old disk system 1303 from switch 1302 and terminates the migration procedure (1506).
- the characteristic of the present preferred embodiment is that a migration program is executed on a migrator configured with a personal computer, workstation, etc. which are connected to a switch.
- a migration program is executed on a migrator configured with a personal computer, workstation, etc. which are connected to a switch.
- FIG. 16 the configuration of the computer system of the present preferred embodiment will be described. However, a description of those configuration elements that are the same as configuration elements of FIG. 1 will be omitted.
- migrator 1606 internally stores the migration program that performs the migration procedure, old configuration information and migration worktable.
- Memory 1637 in new disk system 1604 stores disk unit control program 1639, but does not store the old configuration information, migration worktable and migration program, though in preferred embodiment 1.
- the migration program, old configuration information and migration worktable are not stored in switch 1602.
- FIG. 17 indicates an example configuration ofmigrator 1606.
- Migrator 1606 includes CPU 1701, memory controller 1702, port controller 1706, disk controller 1704, disk drive 1705 and memory 1703.
- CPU 1701 is connected to memory controller 1702, port controller 1706 and disk controller 1704 with internal bus 1701.
- CPU 1701 performs the exchange of control information and data with each controller.
- Port controller 1706 is connected to port controller 1612 of switch 1602 with fiber channel 1605 and performs the exchange of commands and data with switch 1602.
- the port of migrator 1606 is called the N port.
- the port on the switch 1602 side is called the F port.
- Disk drive 1705 is connected to disk controller 1704 and receives read and write requests from CPU 1701.
- Disk drive 1705 stores programs necessary for migrator 1606, and stores migrator program 1731 and migrator worktable 1732 that is necessary during execution of said program.
- Memory 1703 is connected to memory controller 1702. During execution of migration program 1731, this program is read from drive 1705 into memory 1703.
- migration program 1631 of migrator 1606 reads configuration information 1727 from old disk system 1603.
- Configuration information 1727 is the same as that indicated in FIG. 7.
- the port switching procedure is performed. This procedure, similar to that described with preferred embodiment 1, suspends I/O from the host, and exchanges physical port ID 1604 of old disk system 1603 and physical port ID 1402 of new disk system 1604 in port configuration table 1618.
- the control program of switch 1602 sets the port ID status of old disk system 1603 in port configuration table 1618 to "Migrating.” If the status in the port configuration table is "Migrating", the frame is not sent to a port, but instead is passed to migration program 1731 of migrator 1606. Access to old disk system 1603 is performed by migration program 1731 ofmigrator 1606. After these procedures, the I/O of host 1601 is restarted and migration program 1731 of migrator 1606 starts the migration procedure.
- migration program 1731 of migrator 1606 constructs a volume according to the logical volume number and size of said volume which are configured in old disk system 1603, and then initializes variables to be used and migration worktable 1732.
- the procedure thereafter is the same procedure as described in preferred embodiment 1, except that it is not performed by the migration program of the new disk system, but instead by migration program 1731 of migrator 1606.
- switch control program 1619 of switch 1602 changes the status of new disk system 1604 in port configuration table 1618 to "Normal,” as in preferred embodiment 3.
- the operator detaches old disk system 1603 from switch 1602 and terminates the migration procedure.
- a fiber channel connects the migrator and switch.
- a fiber channel connects the migrator and switch.
- the characteristic of the present preferred embodiment is that the host implements the port switching of the switch.
- the host implements the port switching of the switch.
- FIG. 18 an example configuration of the computer system of the present preferred embodiment will be described. However, a description of those configuration elements that are the same as configuration elements of FIG. 1 will be omitted. As will be described later, in the present preferred embodiment, differing from preferred embodiment 1, a port configuration table is provided in host 1801 and a port configuration table is not provided in switch 1802.
- FIG. 19 indicates an example configuration of host 1801.
- Host 1801 comprises CPU 1901, memory controller 1902, port controller 1906, disk controller 1904, drive 1905 and memory 1903.
- CPU 1901 is connected to memory controller 1902, port controller 1906 and disk controller 1904 with internal bus 1907.
- CPU 1901 performs the exchange of control information and data with each controller.
- Port controller 1906 is connected to port controller 1812 of switch 1802 with fiber channel 1805, and performs the exchange of commands and data with switch 1802.
- the port of host 1801 is called the N port, and the port on the switch 1802 side is called the F port.
- Drive 1905 is connected to disk controller 1904 and receives read and write commands from CPU 1901.
- Drive 1905 stores programs necessary for host 1801, and stores operating system 1908, device driver 1909, application program 1910 and port configuration table 1918.
- Memory 1903 is connected to memory controller 1902 and receives read and write requests from CPU 1901.
- Programs such as operating system 1908, disk controller 1904, device driver 1909 that controls the hardware, and application 1910 are read from disk drive 1905 into memory 1903 at the time of each program execution.
- the port switching procedure of the present preferred embodiment performs the same operation both in the case where fabric 301 is configured with a single switch, and in the case where it is configured with a plurality of switches.
- device driver 1909 of the host notifies all hosts 1801 using old disk system 1803 of the start of port switching.
- Device driver 1909 of host 1801 that has received this notification temporarily stores I/O for old disk system 1803 and then queues it in memory 203 of host 1801.
- an I/O process being executed for old disk system 1803 is executed until completed.
- device driver 1909 notifies switch 1802 of I/O suspension completion.
- device driver 1909 of the host that issued the notification of port switching requests all the hosts to exchange physical port ID 602 of old disk system 1803 and physical port ID 602 of new disk system 1804 in port configuration table 1918. Thereafter, the device driver of the host references port configuration table 1918 at each frame transmission or reception and performs the port switching procedure by manipulating S_ID 508 and D_ID 507. This procedure is the same as the procedure described with preferred embodiment 1.
- preferred embodiment 1 through preferred embodiment 5 of the present invention have been described. Appropriate combined embodiments of these preferred embodiments are possible.
- preferred embodiments 3 through 5 an example would be to connect old disk system 1303 and new disk system 1304 with a disk interface for migration, similar to preferred embodiment 2, and perform data migration via this interface.
Abstract
Description
- The present invention relates to a method of additionally attaching a new disk system (migration destination disk system) to a storage area network (hereafter referred to as SAN) and migrating data from an old disk system (migration source disk system), which is already connected to the SAN, to that new disk system and a device thereof.
- Conventional computer systems are configured with a plurality of servers connected by a network such as a LAN and disk units are directly connected to each computer. The data inside each disk unit was managed by the directly connected server. In other words, data was managed in a distributed condition.
- However, the SAN which adopts a configuration in which a plurality of servers, a plurality of disk units, backup units, etc. are connected by a switch or hub has recently become a hot topic. Fiber channels are used to physically connect these units to a switch or hub. The advantages of configuring a system using a SAN are superior scalability and the realization of reduced management cost since unified management can be performed by integrating data distributed over a plurality of disk units. Consequently, a SAN is well suited to a large-scale system. Because many resources are interconnected with a SAN, the management of these resources is an important topic. The management of a logical volume (such as backup), as the management of a disk unit, is one example of that. At present, these management methods are being studied by the SNIA (Storage Networking Industry Association) and NSIC (National Storage Industry Consortium).
- On the other hand, US patent no. 5,680,640 discloses a system and method of migrating data from a first data storage system to a second data storage system. A summary of that is as follows. A first data storage system already connected to a host, network or other data processing system is detached from the aforementioned host and connected to a second data storage system. The aforementioned second data storage system is connected to the aforementioned host or aforementioned data processing system. The aforementioned second data storage system contains a data map or data table that indicates which data element is stored in the aforementioned second storage system and which data in the aforementioned first data storage system has been copied to the aforementioned second storage system. When the aforementioned host, aforementioned network or aforementioned data processing system issues a request for data to the aforementioned second storage system, the aforementioned second data storage system judges whether that data has been stored in the aforementioned second data storage system or in the aforementioned first storage system. If the data has been stored in the aforementioned second data storage system, that data can be used by the host, etc. If the data is not stored in the aforementioned second data storage system, the aforementioned second data storage system issues a request to the aforementioned first data storage system, and that data can be used by the aforementioned host, etc. Then, the aforementioned second data storage system writes that data to its own system and updates the aforementioned data map or aforementioned data table. When the aforementioned second data storage system is not busy, it scans the aforementioned data map or aforementioned data table, determines which data of the aforementioned first data storage system has not yet been copied into its own system, and executes the copying of that data and updating of the aforementioned data map or aforementioned data table.
- According to the data migration system and method disclosed in US patent no. 5,680,640, independent from the aforementioned host, it is possible to execute data migration from the aforementioned first data storage system to the aforementioned second data storage system.
- However, in the aforementioned data migration system and method, when the aforementioned second data storage system is utilized, the procedure of detaching the aforementioned first data storage system from the aforementioned host, connecting it to the aforementioned second data storage system, and connecting the aforementioned second data storage system to the aforementioned host is necessary. Consequently, at least during the interval beginning when the aforementioned first data storage system is detached from the aforementioned host until the aforementioned second data storage system is connected to the aforementioned host and the aforementioned first storage system, the aforementioned host cannot issue I/O (Input/Output) requests. In addition, during that interval it is necessary to temporarily suspend applications or other programs on the aforementioned host that use the aforementioned first data storage system. To further suppress costs associated with data migration, it is necessary to further reduce the time when I/O requests cannot be issued and the time when applications are suspended.
- In addition, in the aforementioned data migration system and method, to connect the aforementioned first data storage system to the aforementioned second data storage system, a channel must be newly provided to each data storage system.
- Further, in US patent no. 5,680,640, a data migration system and method in a SAN environment are not disclosed.
- The object of the present invention is to provide data migration systems and methods that are well suited to a SAN environment.
- An overview of the typical data migration of the present invention is as follows. A host computer and first disk unit are each connected by means of a communication channel to a switch port, and it is assumed that the aforementioned first disk unit receives read/write requests from the aforementioned host computer via the aforementioned switch. Each port of the aforementioned switch is assigned a physical port ID and a logical port ID. The aforementioned switch is provided with a table that maintains the correspondence relation between the physical port ID and the logical port ID. The second disk unit is connected to a port of the aforementioned switch that is different from the port connected to the aforementioned host computer and the port connected to the aforementioned first disk unit. Via the aforementioned switch, the aforementioned second disk unit obtains configuration information (the number of logical volumes and size of each logical volume, for example) of the aforementioned first disk unit. Then, the correspondence relation between the physical port ID and the logical port ID assigned to the port of the switch connected to the aforementioned first disk unit is exchanged with the correspondence relation between the physical port ID and the logical port ID assigned to the port of the switch connected to the aforementioned second disk unit. Concretely, the logical port ID assigned to the port of the switch connected to the aforementioned first disk unit and the logical port ID assigned to the port of the switch connected to the aforementioned second disk unit are exchanged. Consequently, even if the host computer attempts to access the aforementioned first disk unit, in actuality, the aforementioned second disk unit will be accessed. After this port ID switching process is performed, the aforementioned second disk unit is configured with the logical volume that corresponds to the configuration information of the aforementioned first disk, and data in the aforementioned first disk unit is migrated to the aforementioned second disk unit. If there is a read or write request from the aforementioned host computer for data already migrated to the aforementioned second disk unit, that processing is performed for that data by the aforementioned second disk unit. If there is a read or write request from the aforementioned host computer for data that has not yet migrated to the aforementioned second disk unit, that data is read from the aforementioned first disk unit into the aforementioned second disk unit and the processing is performed for that data by the aforementioned second disk unit.
- Other data migration methods provided by this application are clarified with the preferred embodiments of the invention.
- FIG. 1 is a diagram that describes the configuration of the computer system in the first preferred embodiment of the present invention.
- FIG. 2 is a diagram that describes the configuration of the host.
- FIG. 3 is a diagram that describes the fabric configured with one switch.
- FIG. 4 is a diagram that describes the fabric configured with a plurality of switches.
- FIG. 5 is a diagram that describes the frame of the fiber channel.
- FIG. 6 indicate an example configuration of the port configuration table of the present invention: FIG. 6 (A) indicates an example configuration of the port configuration before port switching and FIG. 6 (B) indicates an example configuration of the port configuration after port switching.
- FIG. 7 indicates an example configuration of the old configuration information of the present invention.
- FIG. 8 indicates an example structure of the migration worktable of the present invention.
- FIG. 9 is a flowchart of the data migration procedure of the present invention.
- FIG. 10 is a flowchart of the port switching procedure of the present invention.
- FIG. 11 is a flowchart of the data migration procedure of the present invention.
- FIG. 12 is a diagram that describes the configuration of the computer system in the second preferred embodiment of the present invention.
- FIG. 13 is a diagram that describes the configuration of the computer system in the third preferred embodiment of the present invention.
- FIG. 14 indicates an example configuration of the port configuration table of the third preferred embodiment of the present invention.
- FIG. 15 indicates a flowchart of the data migration procedure of the third preferred embodiment of the present invention.
- FIG. 16 is a diagram that describes the configuration of the computer system in the fourth preferred embodiment of the present invention.
- FIG. 17 indicates an example configuration of the migrator of the present invention.
- FIG. 18 is a diagram that describes the configuration of the computer system in the fifth preferred embodiment of the present invention.
- FIG. 19 is a diagram that describes the configuration of the host in the fifth preferred embodiment of the present invention.
- FIG. 20 is a diagram that describes the correspondence between the physical port ID and logical port ID assigned to each port prior to the port switching procedure of the present invention.
- FIG. 21 is a diagram that describes the correspondence between the physical port ID and logical port ID assigned to each port after the port switching procedure of the present invention.
- FIG. 22 is an example configuration of the case where the management station of the present invention is connected to a LAN.
- Below,
preferred embodiments 1 through 5 propose data migration methods and devices, well suited to a SAN environment. - In the present preferred embodiment, a new disk system is connected to a switch that is already connected to a host and an old disk system, and using that switch, data on the old disk system is migrated to the new disk system. Therefore, because with the present preferred embodiment, there is no need to perform the task of detaching the connection between the host and old disk system and connecting a new disk system to the host and old disk system, and it is only required to connect a new disk system to the switch, compared to the data migration system and method disclosed in the aforementioned US patent no. 5,680,640, the work of adding a new disk system is reduced. Thus, the costs associated with data migration can also be suppressed. In addition, since it is unnecessary to provide a dedicated channel for data migration with the present preferred embodiment, hardware costs can also be reduced.
- Below, the present preferred embodiment will be described using FIG. 1 through FIG. 10.
- FIG. 1 is a diagram that describes the first preferred embodiment of a computer system to which the data migration system and method of the present invention is applied. Two hosts 101,
old disk system 103 andnew disk system 104 are connected withswitch 102, and these form a SAN.Hosts 101,old disk system 103 andnew disk system 104 are connected to switch 102 withfiber channel 105. Since the present invention performs data migration fromold disk system 103 tonew disk system 104, there is no limitation on the number of hosts. - FIG. 5 indicates the frame format that is used with
fiber channel 105. Between SOF (Start Of Frame) 501 that indicates the beginning of the frame and EOF (End Of Frame) 505 that indicates the end,frame header 502,data field 503 and CRC (Cyclic Redundancy Check) 504 are inserted into the frame.Frame header 502 includes frame control information and contains receive side address D_ID (Destination ID) 507, sending source address S_ID (Source ID) 508, R_CTL (Routing Control) 506 that controls the routing,TYPE 510 that indicates the data structure, F_CTL (Frame Control) 511 that controls the frame sequence and exchange, SEQ_ID (Sequence_ID) 512 that distinguishes between the sending source and receive side sequences, SEQ_CNT (Sequence count) 514 that indicates the count value of a number of frames of each sequence, and data field control information DF_CNTL (Data Field Control) 513. Details of the frame offiber channel 105 are shown in ANSI X3.230 FC-PH (Fiber Channel Physical and Signaling Interface). - FIG. 3 indicates a logical network connection configuration of the computer system shown in FIG. 1. In this computer system,
fabric 301 is configured with oneswitch 102.Port 303 ofswitch 102, used in the connection ofhost 101 and the disk units, is called the F (Fabric) port. Also,ports 302 ofhost 101 and the disk units are called N (Node) ports. As indicated in FIG. 4,fabric 301 can also be configured with a plurality ofswitches 102. The switch ports that connect to other switches are called the E (Expansion)ports 401. - In the case where the fabric is configured with a
single switch 102 as in FIG. 3, data transfers fromhost 101 tonew disk system 104 are performed as follows. Host 101 stores its own port ID inS_ID 508, stores the port ID of a frame's sending destination inD_ID 507, and then sends the frame. Whenswitch 102 receives the frame, it examines the port ID which has been stored inD_ID 507 and sends the frame from the F_Port which matches that port ID to the N_Port ofnew disk system 104.S_ID 508 and D_ID are logical port IDs. - Further, as shown in FIG. 4, in the case where
fabric 301 is configured from a plurality ofswitches 102, data transfers fromhost 101 tonew disk system 104 are performed as follows. Whenswitch 102 that is directly connected to host 101 receives a frame fromhost 101, it examines the port ID which has been stored inD_ID 507. However, because that switch does not have the F_Port which matches that port ID, it sends the frame from an E_Port to another switch. Next, the switch that has the F_Port which matches that port ID and is directly connected tonew disk system 104 sends the frame from that F_Port to the N_Port ofnew disk system 104. The data transfers fromhost 101 tonew disk system 104 have been described above as an example, but data transfers are performed in the same manner among other devices. - Again, referencing FIG. 1, the configurations of
switch 102,old disk system 103,new disk system 104 and host 101 will be described in this order. -
Switch 102 includesswitch controller 110,switch module 111 andport controller 112. -
Switch controller 110 performs control withinswitch 102 and includesCPU 114,memory controller 115,memory 116 andnonvolatile memory 117. -
CPU 114, using internal bus 113, performs the exchange of control information and data with each controller. - The read/write access to
nonvolatile memory 117 is controlled bymemory controller 115, and it stores such data as switch control program 119 which is necessary for the control ofswitch 102 and port configuration table 118 which is necessary during execution of that program. - FIG. 6 indicates an example configuration of port configuration table 118. FIG. 6 (A) shows a port configuration table before port switching, and FIG. 6 (B) shows a port configuration table after port switching. The port switching procedure will be described later.
- Port configuration table 118 indicates the port configuration, and includes
logical port ID 601 that indicates the logical port ID andphysical port ID 602 that indicates the physical port ID. In addition, it may also include the rule of the transfer service class of the fiber channel and the port type such as loop. In the present preferred embodiment, as indicated in FIG. 20, it is assumed that ahost 101 is connected to logical port ID_0,old disk system 103 is connected to logical port ID_1, and ahost 101 is connected to logical port ID_3. Also, it is assumed thatnew disk system 104 is connected to logical port ID_2. - The read/write access to
memory 116 is controlled bymemory controller 115. When switch control program 119 is executed byCPU 114, that program is read fromnonvolatile memory 117 and stored inmemory 116. Further, at that time and as necessary,CPU 114 also reads port configuration table 118 fromnonvolatile memory 117 and stores it inmemory 116. -
Port controller 112 performs control of the data coding/compounding. Concretely,port controller 112 extracts serial data from a received fiber channel frame and converts it into parallel data, and extracts information necessary for switching such as the send destination ID from the frame and sends it to switchmodule 111. Also,port controller 112 performs the reverse procedure. -
Switch module 111 has a plurality of ports that are individually connected to a plurality ofport controllers 112.Switch module 111 is connected toCPU 114 via internal bus 113 and is controlled byCPU 114. Whenswitch module 111 receives data fromport controller 112, in accordance with the send destination ID of that data, it switches a port to the output port and sends data.Switch module 111 may be made with a crossbar switch. -
Management station 150, connected to switch 102, sets the various parameters ofswitch 102, and performs control of the migration process which is the most characteristic function of the present preferred embodiment and information management. Further,management station 150 has the command to active the migration program (to be described later) onnew disk system 104 and the command to acquire migration information (such as migrating, done, or error). - In FIG. 1,
management station 150 is directly connected to switch 102. However, as shown in FIG. 22, the aforementioned settings may be implemented with the Web or other means, by connectinghost 101,switch 102,old disk system 103,new disk system 104 andmanagement station 150 to a LAN (Local Area Network). - In present preferred embodiment, in order to simplify the description,
old disk system 103 andnew disk system 104 are assumed to have the same configuration, except for programs and information in memory. -
Old disk system 103 includesdisk control unit 120 anddisk unit 121. -
Disk unit 121 includes a plurality of disk drives 130. These disk drives 130 are connected todisk controller 124 with interface (I/F) 129 (fiber channel, SCSI, etc.). In the implementation of the present invention, the number ofdisk drives 130 is not restricted. -
Disk controller 120 includesCPU 122,memory controller 123,port controller 125,disk controller 124 andmemory 126.CPU 122,memory controller 123,port controller 125 anddisk controller 124 are connected with an internal bus. -
CPU 122, using the internal bus, performs the exchange of control information and data with these controllers.CPU 122 issues read and write commands todisk drive 130 that is necessary in the processing of commands sent fromhost 101 viaswitch 102.CPU 122 constructs the well-knownRAID 0~5 configuration with a plurality ofdisk drives 130, and provides logical volumes forhost 101. -
Port controller 125 is connected toport controller 112 ofswitch 102 byfiber channel 105 and has the same functions asport controller 112. -
Memory 126 is connected tomemory controller 123 and stores diskunit control program 128 that controls the disk unit, data that are necessary during execution of said program, andconfiguration information 127.Configuration information 127 will be described later. Diskunit control program 128 is executed byCPU 122 and is a program that controlsport controller 125 anddisk controller 124, and processes read/write commands received fromhost 101. - As described above, except for the program and information in
memory 137, the configuration elements ofnew disk system 104 are the same as the configuration elements ofold disk system 103. Therefore only the program and information inmemory 137 will be described. Stored inmemory 137 isold configuration information 138 which has been read and transferred fromconfiguration information 127 stored inmemory 126 ofold disk system 103,migration program 142 used during data migration, andmigration worktable 143 that indicates the state of the data migration. - FIG. 8 indicates an example structure of
migration worktable 143.Migration worktable 143 includesvolume number 801,slot number 802 andstatus 803 that indicates the status of said slot. - FIG. 2 indicates the configuration of
host 101.Host 101 includesCPU 201,memory controller 202,port controller 206,disk controller 204, disk drive 205 andmemory 203. -
CPU 201,memory controller 202,port controller 206 anddisk controller 204 are connected withinternal bus 207.CPU 201, usinginternal bus 207, performs the exchange of control information and data with these controllers. -
Port controller 206 is connected toport controller 112 ofswitch 102 withfiber channel 105 and performs the exchange of commands and data withport controller 112. - Disk drive 205 is connected to
disk controller 204 andstores operating system 208,device driver 209 that controls hardware such asport controller 206,application program 210 and data that is necessary during execution of these programs. -
Memory 203 is connected tomemory controller 202. When operatingsystem 208,disk controller 204,device driver 209,application program 210, etc. are executed byCPU 201, they are read from disk drive 205 and stored inmemory 203. - Next, referencing FIG. 9, the data migration procedure of the present invention will be described. It is assumed that
host 101 andold disk system 103 have been already connected to switch 102. - First, an operator activates
management station 150 and then inputs the port numbers ofswitch 102 that are connected toold disk system 103 andnew disk system 104. - Next, the operator connects
new disk system 104 to switch 102. At this point in time, if the port ID ofnew disk system 104 is a port ID other than a port ID already in use, any port ID may be assigned. When each port ofswitch 102 is assigned a port ID by default, the port ID assigned to the F_Port connected tonew disk system 104 is appropriate. In the present preferred embodiment, as described above, logical port ID_2 is assigned tonew disk system 104. - Because the logical port ID assigned to
new disk system 104 is different from logical port ID_1 of the disk unit that can be used byhost 101, at this point in time, host 101 cannot accessnew disk system 104. - After connecting
new disk system 104, the operator activatesmigration program 142 onnew disk system 104 with the aforementioned command frommanagement station 150. The activatedmigration program 142 first obtainsconfiguration information 127 from old disk system 103 (902). - As indicated in FIG. 7,
configuration information 127 includesold port ID 702, worldwide name 703,fiber configuration information 704 andSCSI configuration information 705. -
Fiber configuration information 704 includesPLOGI payload 706 andPRLI payload 707. -
PLOGI payload 706 includescommon service parameter 708 that are exchanged at the time of a fiber channel N_Port login (PLOGI),port name 709,node name 710 andclass service parameter 711. Specified incommon service parameter 708 are the fiber channel version information and functions such as the address specification method supported by said fiber channel device, the communication method, etc.Class service parameter 711 indicates the class support information, X_ID re-assignment, ACK capability, etc. Details of fiber channel parameters are described in the aforementioned ANSI X3.230 FC-PH.PRLI payload 707 includesservice parameter 712. -
SCSI configuration information 705 includesinquiry data 703, disconnect/reconnectparameter 714, sense data 715 and modeselect parameter 716.Inquiry data 713 indicates the type, vendor ID, product ID, etc. of the SCSI device. Disconnect/reconnectparameter 714 indicates the connection conditions. When an error occurs, sense data 715 is exchanged to investigate the state of the disk unit. Modeselect parameter 716 performs the setting and modification of various parameters related to the physical attributes of the SCSI device, data format of the storage media, error recovery method and procedure, processing method of an I/O process, etc. By means ofinquiry data 713 and modeselect parameter 716, the number of volumes and size of each volume (number of blocks) onold disk system 103 can be learned. A detailed description of the protocol for SCSI onfiber channel 105 is shown in ANSI X.269 Fiber Channel Protocol for SCSI. - As described above,
configuration information 127 can also exist as information in addition to that which can be acquired using protocols of the existing fiber channel, SCSI, etc. If that type of configuration information exists, the operator directly readsconfiguration information 127 fromold disk system 103 and transfers it tonew disk system 104. Reading and transferring are performed from an operation panel or by web access by means of HTTP. - When the transfer of
configuration information 127 tonew disk system 104 is completed, or in other words, when the transfer ofold configuration information 138 is completed,migration program 142 ofnew disk system 104 notifies switch 102 of that fact. - When switch control program 119 of
switch 102 receives that notification, the port switching procedure is started. - Details of the port switching procedure are described using the flowchart of FIG. 10.
- Initially, the case as indicated in FIG. 3 where
fabric 301 is configured with asingle switch 102 will be described. - First, switch control program 119 of
switch 102 notifies allhosts 101 usingold disk system 103 that port switching has begun.Device driver 209 ofhost 101 that has received this notification queues an I/O process forold disk system 103 inmemory 203 of host 101 (1001). - When an I/O process for
old disk system 103 is suspended,device driver 209 notifiesswitch 102 of the I/O suspension completion. If an I/O process forold disk system 103 is being executed, it may be terminated, but it is desirable to allow the execution to finish and then issue notification of the I/O suspension completion. After receiving such notification from allhosts 101, switch control program 119 ofswitch 102 changes the correspondence relation betweenlogical port ID 601 andphysical port ID 602 ofold disk system 103 and the correspondence relation betweenlogical port ID 601 andphysical port ID 602 ofnew disk system 104 of port configuration table 118 (1002). In other words, port configuration table 118 is rewritten as in FIG. 6 (B). Using diagrams of the whole computer system, this situation can be illustrated as the change from the state indicated in FIG. 20 to the state indicated in FIG. 21. - Thereafter, by means of referencing port configuration table 118 at each frame transmission or reception,
port controller 112 ofswitch 102 performs the port switching procedure by manipulatingS_ID 508 andD_ID 507. When a frame is received,logical port ID 601 that corresponds to S_ID 508 of the frame is retrieved, andS_ID 508 of the frame is converted intophysical port ID 602 that corresponds to the retrievedlogical port ID 601. Similarly, when a frame is transmitted,logical port ID 601 that corresponds to D_ID 507 of the frame is retrieved, and thatD_ID 507 is converted intophysical port ID 602 that corresponds to the retrievedlogical port ID 601. At this time,CRC 504 that is appended to the frame is recalculated. By means of the above procedure, all frames toold disk system 103 are sent tonew disk system 104. Further, frames sent fromnew disk system 104 are viewed byhost 101 as being sent fromold disk system 103. After port switching byswitch 102, host 101 I/O is restarted (1003). - Next, as indicated in FIG. 4, the case where
fabric 301 is configured with a plurality ofswitches 102 will be described. - First, switch 102 which will become the master (master switch) is determined. In the present preferred embodiment, the master switch is
switch 102 that is directly connected tonew disk system 104. - Switch control program 119 of the master switch notifies all
hosts 101 that are usingold disk system 103 and all switches except for the master switch infabric 301 of the starting of port switching. The processing to be performed bydevice driver 209 ofhost 101 that has received such notification is the same as in the case where the fabric is configured from asingle switch 102, except for notification to the master switch of the I/O suspension completion. - After such notification is received from all
hosts 101, switch control program 119 of the master switch changes the correspondence relation betweenlogical port ID 601 andphysical port ID 602 ofold disk system 103 and the correspondence relation betweenlogical port ID 601 andphysical port ID 602 ofnew disk system 104 of port configuration table 118, and notifies allswitches 102 except the master switch of that change. Based on such notification, all switches except for the master switch change their own port configuration table 118. Thereafter, the operation of each switch is the same as the operation ofswitch 102 in the case where the fabric is configured with asingle switch 102. After port switching has been performed by allswitches 102 infabric 301, host 101 I/O is restarted. - The data migration procedure is performed synchronously with the completion of the port switching procedure. This data migration procedure will be described using the flowchart of FIG. 11.
- First,
migration program 142 constructs a volume innew disk system 104 that corresponds to the logical volume number and size of that volume inold disk system 103, and then initializes variables to be used andmigration worktable 143 that was described with FIG. 8 (1101). -
Migration program 142 onnew disk system 104 checks whether there is an I/O request from host 101 (1102). - If there is no I/O request from
host 101, data is migrated in slot units fromold disk system 103. At that time, usingmigration worktable 143,migration program 142 computes the address of the next data to migrate (1103). - Data migration is performed for all the logical volumes of
old disk system 103 in order of increasingvolume number 801. Further, within each volume, data migration is performed beginning with the first block.Worktable 143 for migration shown in FIG. 8 indicates the next migration address in thevolume number 801 cell of the first row. The initial value of the next migration address is the first block address of thesmallest volume number 801. Moreover,migration worktable 143 indicates the next migration slot in theslot number 802 cell of the first row. From the second row onward, the rows are arranged in order of increasingvolume number 801 andslot number 802. Whenmigration program 142 transfers data of the next migration address obtained frommigration worktable 143, it changesstatus 803 of that slot number to "Migrating" (1104). - Next, using
port controller 125,migration program 142 issues a request to read the slot size toold disk system 103 and acquires the corresponding data (1105). -
Migration program 142 writes the data obtained fromold disk system 103 to a corresponding volume ofnew disk system 104 ondisk drive 141, usingdisk controller 124 and via I/F 140 (1106). - After the data is written on
disk drive 141, it is checked whether the migration of all slots of the corresponding volume is completed. If completed, data migration of the next volume is executed. If not completed, the slot number is incremented (1107). - If the migration of all volumes is completed, the migration procedure is finished (1108).
- Next, the case of an I/O request from
host 101 will be described. If there is an I/O request fromhost 101,migration program 142 investigates whether the request is for a read or write access (1109). - In the case of a read request,
migration program 142references migration worktable 143 and investigates whether migration of the requested data has been completed (1110). - If the migration is completed,
migration program 142 reads that data fromdisk drive 141 innew disk system 104 and sends it back to host 101 (1113, 1112). - If the migration of the data requested from
host 101 is not complete, usingport controller 125,migration program 142 issues a read request toold disk system 103 viaswitch 102 and acquires said data.Migration program 142 sends back the data acquired fromold disk system 103 to host 101 and also writes that data to the corresponding volume of new disk system 104 (1111, 1112). - After said data is written on
disk drive 141, said data is registered intomigration worktable 143, and withstatus 803 set to "Done", the processing of said request is finished (1108). - Next, the case of a write request from
host 101 will be described.Migration program 142 receives data related to the write request from host 101 (1114). - Then, using
port controller 125,migration program 142 issues a read request in slot size units toold disk system 103 viaswitch 102 so as to include the data requested fromhost 101, and acquires the data. Aftermigration program 142 overwrites the data obtained from the migration source with the data received fromhost 101 and creates new slot data, it writes to the volume innew disk system 104 requested by host 101 (1115). - After the write is completed,
migration program 142 registers said slot intomigration worktable 143, and withstatus 803 set to "Done", the processing related to the write request fromhost 101 is finished (1107). - After the data migration procedure is completed, the operator detaches
old disk system 103 from the switch and terminates the migration procedure (905). - The system configuration and flow of the data migration procedure have been described above for
preferred embodiment 1. By means of the present preferred embodiment, I/O requests from the host are only suspended during the time while configuration information ofold disk system 103 is being transferred tonew disk system 104 and during the time while the port switching procedure is being performed. Therefore, by means of the present preferred embodiment, because there is no need to perform the task of connecting a new disk system to the host and old disk system, by detaching the connection between the host and old disk system, the time while I/O requests from the host are suspended is shorter than the time while I/O requests from the host are suspended in the data migration system and method disclosed in US patent no. 5,680,640. Consequently, the costs associated with data migration can be suppressed. Moreover, by means of the present preferred embodiment, since there is no need to provide a dedicated channel for data migration, hardware costs can also be suppressed. - The present preferred embodiment differs from
preferred embodiment 1 in that in addition to the system configuration described withpreferred embodiment 1, the old disk system and new disk system are directly connected with an interface (fiber channel or SCSI, for example). In the present preferred embodiment, since data migration is performed using that interface, compared topreferred embodiment 1, high-speed data migration can be performed. In the present preferred embodiment, it is necessary to provide an interface for data migration. However, there is no need to perform the task of connecting a new disk system to the host and old disk system, by detaching the connection between the host and old disk system, and because it is only required to connect a new disk system to the switch and connect the old disk system and the new disk system with an interface, compared to the data migration system and method disclosed in the aforementioned US patent no. 5,680,640, the work of adding the new disk system is reduced. - Below, the present embodiment will be described using FIG. 12.
- FIG. 12 is a diagram that describes the second preferred embodiment of a computer system that has adopted the data migration system and method of the present invention. As described above, each configuration element of the computer system is the same as each configuration element of FIG. 1, and therefore their descriptions are omitted.
- Below, the flow of the data migration procedure in the present preferred embodiment will be described. The data migration procedure flow is the same as that of
preferred embodiment 1, which was described with FIG. 9. However, in the present preferred embodiment, sinceold disk system 1203 andnew disk system 1204 are connected directly by a interface and data migration is performed using that interface, it is necessary to obtain the correspondence relation between the logical address and physical address inold disk system 1203 fromold configuration information 1238. Below, only this point of difference will be described. - In
steps 1105, 1113 and 1115 of FIG. 11, data is read from the old disk system viaswitch 102. However, in the present preferred embodiment, using information that is included inold configuration information 1238,migration program 1231 computes the physical address corresponding to the logical address of the data that should be read fromold disk system 1203. Then, using I/F 1240,migration program 1231 issues directly a read request todisk drive 1230 ofold disk system 1203 that corresponds to the computed physical address, and acquires that data. At this time, if that data has been distributed to a plurality ofdisk drives 1230 ofold disk system 1203, or if stored in dispersed physical addresses, a plurality of read requests will be issued. - In the present preferred embodiment, since
old disk system 1203 andnew disk system 1204 are connected directly with an interface, and data migration is performed using that interface without passing throughswitch 1202, compared topreferred embodiment 1, high-speed data migration can be performed. Further, since the data migration of the present preferred embodiment does not pass throughswitch 1202, the resource consumption of the switch can be suppressed. In the present preferred embodiment, two hosts and two disk units are connected to switch 1202. However, because many hosts and disk units are connected in a SAN environment, those resources can be allocated to the data transfer between other hosts and other disk units. Therefore, by means of the present preferred embodiment, compared topreferred embodiment 1, the degradation of switch performance that accompanies data migration can be suppressed. - The present preferred embodiment differs from
preferred embodiment 1 in that the migration program is executed by a switch. By means of the present preferred embodiment, since it is unnecessary for a disk unit to have a migration program, data migration from an old disk system is possible even with a disk unit that does not have this type of program. - Using FIG. 13, the configuration of the computer system of the present preferred embodiment will be described. However, a description of those configuration elements that are the same as configuration elements of FIG. 1 will be omitted.
- In the present preferred embodiment,
non-volatile memory 1317 inswitch 1302 stores switch control program 1319 that is necessary for control ofswitch 1302,migration program 1342 that performs the migration procedure, port configuration table 1318 that is necessary during execution of these programs, old configuration information 1327 andmigration worktable 1343. Diskunit control program 1339 is stored inmemory 1337 innew disk system 1304, but the old configuration information, migration worktable, and migration program are not stored, though they are inpreferred embodiment 1. - FIG. 14 is an example configuration of port configuration table 1318 that indicates the port configuration. Port configuration table 1318 includes
logical port ID 1401 that indicates the virtual port ID,physical port ID 1402 that indicates the physical port ID, andstatus 1403 that indicates the port status. - Next, using the flowchart of FIG. 15, the data migration procedure of the present preferred embodiment will be described.
- An operator connects
new disk system 1304 to switch 1302 (1501). This step is the same asstep 901 of FIG. 9. - Next,
migration program 1342 ofswitch 1302 reads configuration information 1327 from old disk system 1303 (1502). Configuration information 1327 is the same as that shown in FIG. 7. - After configuration information 1327 of
old disk system 1303 has been transferred to switch 1302, switch control program 1319 ofswitch 1302 starts the port switching procedure (1503). - Also in the port switching procedure of the present preferred embodiment, similar to
preferred embodiment 1, after the host I/O is stopped, the correspondence relation betweenlogical port ID 1401 andphysical port ID 1402 ofold disk system 1303 and the correspondence relation betweenlogical port ID 1401 andphysical port ID 1402 ofnew disk system 1304 of port configuration table 1318 are changed. However, the port switching procedure of the present preferred embodiment differs from that ofpreferred embodiment 1 in the following point. In the present preferred embodiment, switch control program 1319 ofswitch 1302 setsport ID status 1403 ofold disk system 1303 in port configuration table 1318 to "Migrating." The frame for the port ID with "Migrating"status 1403 in port configuration table 1318 is not sent to the corresponding port, but instead is passed tomigration program 1331 ofswitch 1302. In other words, access toold disk system 1303 is performed bymigration program 1331 ofswitch 1302. - In the case where the fabric is configured with a plurality of
switches 1302, using the same method aspreferred embodiment 1, after the host I/O is stopped, switch control program 1319 of the master switch setsport ID status 1403 ofold disk system 1303 in port configuration table 1318 to "Migrating." The frame for the port ID with "Migrating"status 1403 in port configuration table 1318 is not sent to the corresponding port, but instead is passed tomigration program 1331 ofswitch 1302. In the case where the fabric is configured with a plurality ofswitches 1302, it is sufficient if at least old configuration information 1327,migration worktable 1343, andmigration program 1342 are provided inswitch 1302, the master switch. - After the port switching procedure is completed, the data migration procedure is performed. First,
migration program 1342 ofswitch 1302 constructs a volume according to the logical volume number and size of said volume which are configured inold disk system 1303, and then initializes variables to be used andmigration worktable 1332 that is shown with FIG. 8. The procedure thereafter is the same procedure as described inpreferred embodiment 1, except that it is not performed by the migration program of the new disk system, but instead bymigration program 1302 ofswitch 1302. - After the data migration procedure is completed, switch control program 1319 of
switch 1302 changes the status ofnew disk system 1304 in port configuration table 1318 to "Normal" (1505). The operator detachesold disk system 1303 fromswitch 1302 and terminates the migration procedure (1506). - The characteristic of the present preferred embodiment is that a migration program is executed on a migrator configured with a personal computer, workstation, etc. which are connected to a switch. By means of the present preferred embodiment, similar to
preferred embodiment 3, since it is unnecessary for a new disk system to have a migration program, data migration from an old disk system is possible even with a disk unit that does not have this type of program. Further, in the present preferred embodiment, as inpreferred embodiment 3, since the migration program is not executed on a switch, a load of the switch can be reduced. - Using FIG. 16, the configuration of the computer system of the present preferred embodiment will be described. However, a description of those configuration elements that are the same as configuration elements of FIG. 1 will be omitted.
- A characteristic of the present preferred embodiment, as will be described later, is that migrator 1606 internally stores the migration program that performs the migration procedure, old configuration information and migration worktable.
Memory 1637 innew disk system 1604 stores diskunit control program 1639, but does not store the old configuration information, migration worktable and migration program, though inpreferred embodiment 1. Further, different frompreferred embodiment 3, in the present preferred embodiment, the migration program, old configuration information and migration worktable are not stored inswitch 1602. - FIG. 17 indicates an
example configuration ofmigrator 1606.Migrator 1606 includesCPU 1701,memory controller 1702,port controller 1706,disk controller 1704,disk drive 1705 andmemory 1703.CPU 1701 is connected tomemory controller 1702,port controller 1706 anddisk controller 1704 withinternal bus 1701.CPU 1701 performs the exchange of control information and data with each controller.Port controller 1706 is connected toport controller 1612 ofswitch 1602 withfiber channel 1605 and performs the exchange of commands and data withswitch 1602. The port ofmigrator 1606 is called the N port. The port on theswitch 1602 side is called the F port.Disk drive 1705 is connected todisk controller 1704 and receives read and write requests fromCPU 1701.Disk drive 1705 stores programs necessary formigrator 1606, and storesmigrator program 1731 and migrator worktable 1732 that is necessary during execution of said program.Memory 1703 is connected tomemory controller 1702. During execution ofmigration program 1731, this program is read fromdrive 1705 intomemory 1703. - Next, the flow of the data migration procedure of the present preferred embodiment will be described. An operator connects
new disk system 1604 to switch 1602 for data migration. At this time, the port ID ofnew disk system 1604 takes the same value as the port ID assigned to the F_Port ofswitch 1602, andnew disk system 1604 is not recognized from host 1601. This step is the same asstep 901 described in FIG. 9. - Next,
migration program 1631 ofmigrator 1606 readsconfiguration information 1727 fromold disk system 1603.Configuration information 1727 is the same as that indicated in FIG. 7. - After
configuration information 1727 ofold disk system 1603 is transferred to the migrator, the port switching procedure is performed. This procedure, similar to that described withpreferred embodiment 1, suspends I/O from the host, and exchangesphysical port ID 1604 ofold disk system 1603 andphysical port ID 1402 ofnew disk system 1604 in port configuration table 1618. The control program ofswitch 1602 sets the port ID status ofold disk system 1603 in port configuration table 1618 to "Migrating." If the status in the port configuration table is "Migrating", the frame is not sent to a port, but instead is passed tomigration program 1731 ofmigrator 1606. Access toold disk system 1603 is performed bymigration program 1731ofmigrator 1606. After these procedures, the I/O of host 1601 is restarted andmigration program 1731 of migrator 1606 starts the migration procedure. - After the port switching procedure is completed, the data migration procedure is performed. First,
migration program 1731 ofmigrator 1606 constructs a volume according to the logical volume number and size of said volume which are configured inold disk system 1603, and then initializes variables to be used and migration worktable 1732. The procedure thereafter is the same procedure as described inpreferred embodiment 1, except that it is not performed by the migration program of the new disk system, but instead bymigration program 1731 ofmigrator 1606. - After the data migration procedure is completed, switch control program 1619 of
switch 1602 changes the status ofnew disk system 1604 in port configuration table 1618 to "Normal," as inpreferred embodiment 3. The operator detachesold disk system 1603 fromswitch 1602 and terminates the migration procedure. - In addition, in the present preferred embodiment, a fiber channel connects the migrator and switch. However, it can be easily understood by those skilled in the art of the present invention that the effect of the present preferred embodiment can be obtained with connection by such means as a vendor-unique bus.
- The characteristic of the present preferred embodiment is that the host implements the port switching of the switch. By means of the present preferred embodiment, there is no need to provide a port configuration table in the switch, though in
preferred embodiment 1 through preferredembodiment 4. Therefore, it is possible to perform data migration even in cases where a SAN is configured using a switch that does not have this function. - Using FIG. 18, an example configuration of the computer system of the present preferred embodiment will be described. However, a description of those configuration elements that are the same as configuration elements of FIG. 1 will be omitted. As will be described later, in the present preferred embodiment, differing from
preferred embodiment 1, a port configuration table is provided inhost 1801 and a port configuration table is not provided inswitch 1802. - FIG. 19 indicates an example configuration of
host 1801.Host 1801 comprisesCPU 1901,memory controller 1902,port controller 1906,disk controller 1904,drive 1905 andmemory 1903.CPU 1901 is connected tomemory controller 1902,port controller 1906 anddisk controller 1904 withinternal bus 1907.CPU 1901 performs the exchange of control information and data with each controller.Port controller 1906 is connected toport controller 1812 ofswitch 1802 withfiber channel 1805, and performs the exchange of commands and data withswitch 1802. The port ofhost 1801 is called the N port, and the port on theswitch 1802 side is called the F port.Drive 1905 is connected todisk controller 1904 and receives read and write commands fromCPU 1901. Drive 1905 stores programs necessary forhost 1801, andstores operating system 1908,device driver 1909,application program 1910 and port configuration table 1918.Memory 1903 is connected tomemory controller 1902 and receives read and write requests fromCPU 1901. Programs such asoperating system 1908,disk controller 1904,device driver 1909 that controls the hardware, andapplication 1910 are read fromdisk drive 1905 intomemory 1903 at the time of each program execution. - Next, the flow of the data migration procedure of the present preferred embodiment will be described. This flow is the same as the flow of the data migration procedure of
preferred embodiment 1, which is shown in FIG. 9. However, in the present preferred embodiment, the port switching procedure is different from that of preferred embodimentl. Here, only the port switching procedure will be described. - The port switching procedure of the present preferred embodiment performs the same operation both in the case where
fabric 301 is configured with a single switch, and in the case where it is configured with a plurality of switches. At first, by operator command,device driver 1909 of the host notifies allhosts 1801 usingold disk system 1803 of the start of port switching.Device driver 1909 ofhost 1801 that has received this notification temporarily stores I/O forold disk system 1803 and then queues it inmemory 203 ofhost 1801. On the other hand, an I/O process being executed forold disk system 1803 is executed until completed. When an I/O process forold disk system 1803 is suspended,device driver 1909 notifiesswitch 1802 of I/O suspension completion. After receiving I/O suspension completion notification from allhosts 1801,device driver 1909 of the host that issued the notification of port switching requests all the hosts to exchangephysical port ID 602 ofold disk system 1803 andphysical port ID 602 ofnew disk system 1804 in port configuration table 1918. Thereafter, the device driver of the host references port configuration table 1918 at each frame transmission or reception and performs the port switching procedure by manipulatingS_ID 508 andD_ID 507. This procedure is the same as the procedure described withpreferred embodiment 1. - Above,
preferred embodiment 1 through preferred embodiment 5 of the present invention have been described. Appropriate combined embodiments of these preferred embodiments are possible. Forpreferred embodiments 3 through 5, an example would be to connectold disk system 1303 andnew disk system 1304 with a disk interface for migration, similar topreferred embodiment 2, and perform data migration via this interface. - As described above, data migration methods and devices well suited to a SAN environment can be provided by means of this invention.
- Although the present invention has been described in connection with the preferred embodiments thereof, many other variations and modification will become apparent to those skilled in the art.
Claims (14)
- A method of migrating data from a first storage system that is connected to a switch (102) by means of a communication channel and receives read/write requests from a host computer (101) connected to the switch (102) by means of a communication channel, to a second storage system, comprising the steps of:connecting the second storage system to the switch (102) by means of a communication channel; and,writing, via the switch (102), data stored in the first storage system to the second storage system.
- A method of migrating data from a first storage system that is connected to a switch (102) by means of a communication channel and receives read/write requests from a host computer (101) connected to the switch (102) by means of a communication channel, to a second storage system, comprising the steps of:connecting the second storage system to the switch (102) by means of a communication channel;reading the number of logical volumes constructed in the first storage system and their sizes are read into the second storage system via the switch (102);constructing the same number and same sizes of logical volumes as logical volumes that have been constructed in the first storage system in the second storage system; and,writing, via the switch (102), data stored in the first storage system to the second storage system in volume units.
- A method of migrating data from a first storage system that is connected to one port of a switch (102) provided with a plurality of ports each assigned its own port identifier by means of a communication channel and receives, via the switch (102), read/write requests from a host computer (101) connected to another port of said switch (102) by means of a communication channel, to a second storage, the method comprising the steps of:connecting the second storage system, by means of a communication channel, to a port, of said switch (102), other than the ports connected to the first disk unit and to the host computer (101);mutually exchanging the port identifier assigned to the port connected to the first storage system and the port identifier assigned to the port connected to the second storage system;writing the data in the first storage system to the second storage system via the switch;if, from said host computer (101), there is a read or write request for the first storage system, sending the request to the second storage system; and,if the data for the read or write request has been written already to the second storage system, performing read or write processing of the already written data by means of the second storage system, and if the data for the read or write request has not yet been written to the second storage system, writing the data for the read or write request to the second storage system, and performing read or write processing of the written data by means of the second storage system.
- A data migration method according to claim 3, further comprising the steps of:directly connecting the first storage system and the second storage system by means of a communication channel; and,without passing through the switch, writing data in the first storage system to the second storage system via the communication channel that directly connects the first storage system and the second storage system.
- A data migration method of migrating data from a first storage system that is connected to one port of a switch provided with a plurality of ports each assigned its own port identifier by means of a communication channel and receives, via the switch, read/write requests from a host computer connected to another port of said switch by means of a communication channel, to a second storage, the method comprising the steps of:connecting the second storage system to a port, of the switch, other than the ports connected to the first storage system and to the host computer, by means of a communication channel;mutually exchanging the port identifier assigned to the port connected to the first storage system and the port identifier assigned to the port connected to the second storage system;reading information on logical volumes constructed in the first storage system;constructing the same number and same sizes of logical volumes as logical volumes that have been constructed in the first storage system in the second storage subsystem;writing data stored in the first storage system to the second storage system via the switch;managing completion of said writing from the first storage system to the second storage system in volume units;if, from said host computer, there is a read or write request for the first storage system, sending the request to the second storage system; and,if the data for the read or write request has been written already to the second storage system, performing read or write processing of the already written data by means of the second storage system, and if the data for the read or write request has not yet been written to the second storage system, writing the data for the read or write request to the second storage system, and performing read or write processing of the written data by means of the second storage system.
- A data migration method according to claim 5.
wherein the second storage system reads, via the switch, the logical volume information from the first storage system and manages the completion of said writing to the second storage system in volume units. - A data migration method according to claim 5,
wherein the switch reads the logical volume information from the first storage system, constructs the same number and same sizes of logical volumes as logical volumes that have been constructed in the first storage system, in the second storage system, and manages the completion of said writing to the second storage system in volume units. - A data migration method according to claim 5,
wherein an information processing unit connected to the switch reads the logical volume information from the first storage system, constructs the same number and same sizes of logical volumes as logical volumes that have been constructed in the first storage system, in the second storage system, and manages the completion of said writing to the second storage system in volume units. - A data migration method of migrating data from a first storage system that is connected to one port of a switch provided with a plurality of ports each assigned its own port identifier by means of a communication channel and receives, via the switch, read/write requests from a host computer connected to another port of said switch by means of a communication channel, to a second storage, the method comprising the steps of:connecting the second storage system to a port, of the switch, other than the ports connected to the first disk unit and to the host computer, by means of a communication channel;switching the destination of a read/write request from the host computer from the first storage system to the second storage system;writing data in the first storage system to the second storage system via the switch; and,if the data for a read or write request from the host computer has been written already to the second storage system, performing read or write processing of the already written data by means of the second storage system, and if the data for the read or write request has not yet been written to the second storage system, writing the data for the read or write request to the second storage system, and performing read or write processing of the written data by means of said second storage system.
- A data migration method according to claim 9, further comprising the steps of:reading the number of logical volumes constructed in the first storage system and their sizes;constructing the same number and same sizes of logical volumes as logical volumes that have been constructed in the first storage system in the second storage system; and,writing, in volume units, data stored in the first storage system to the second storage system via the switch.
- A data migration method according to claim 10,
wherein the second storage system manages the completion of said writing to the second storage system in volume units. - A data migration method according to claim 1,
wherein the communication channel connecting between the switch and the first storage system, the communication channel connecting between the switch and the second storage system and communication channel connecting between the switch and the host computer are fiber channels. - A disk storage system to which data stored in other storage system connected to a switch is migrated via the switch, comprising:a port for connecting to the switch,a program for reading data stored in the other storage system via the switch, if data for a read or write request from a host computer that is connected to the switch has been read already, performing read or write processing of the already read data, and if the data for the read or write request has not yet been read, reading the data for the read or write request from the other storage system.
- A computer connected to a switch to which a first storage system is connected, comprising:a port for connecting to the switch,a program, in case that a second storage system to which data stored in the first storage system is migrated via the switch is connected to the switch, for changing the destination of a read or write request from the first storage system to the second storage system.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2000063289 | 2000-03-03 | ||
JP2000063289A JP3918394B2 (en) | 2000-03-03 | 2000-03-03 | Data migration method |
Publications (2)
Publication Number | Publication Date |
---|---|
EP1130514A2 true EP1130514A2 (en) | 2001-09-05 |
EP1130514A3 EP1130514A3 (en) | 2007-12-05 |
Family
ID=18583179
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP00119434A Withdrawn EP1130514A3 (en) | 2000-03-03 | 2000-09-14 | Data migration method using storage area network |
Country Status (3)
Country | Link |
---|---|
US (1) | US6976103B1 (en) |
EP (1) | EP1130514A3 (en) |
JP (1) | JP3918394B2 (en) |
Cited By (36)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1310876A1 (en) * | 2000-05-18 | 2003-05-14 | Hitachi, Ltd. | Computer system |
EP1347366A2 (en) * | 2002-03-20 | 2003-09-24 | Hitachi, Ltd. | Storage system, disk control cluster, and a method for increasing the number of disk control clusters in a storage system |
US6708232B2 (en) | 2000-06-29 | 2004-03-16 | Hitachi, Ltd. | Data migration method, protocol converter and switching apparatus using it |
EP1569115A2 (en) | 2004-02-26 | 2005-08-31 | Hitachi, Ltd. | Data migration method and apparatus |
EP1589412A2 (en) * | 2001-11-13 | 2005-10-26 | Hitachi, Ltd. | Computer data migration system |
WO2006069178A2 (en) * | 2004-12-20 | 2006-06-29 | Emc Corporation | A method to perform parallel data migration in a clustered storage environment |
US7096338B2 (en) | 2004-08-30 | 2006-08-22 | Hitachi, Ltd. | Storage system and data relocation control device |
WO2006099826A2 (en) * | 2005-03-23 | 2006-09-28 | Fujitsu Siemens Computers Gmbh | Method for removing a mass storage system from a computer network, and computer program product and computer network for carrying out the method |
WO2007076385A1 (en) * | 2005-12-27 | 2007-07-05 | Emc Corporation | On-line data migration of a logical/virtual storage array |
US7366853B2 (en) * | 2002-11-25 | 2008-04-29 | Hitachi, Ltd. | Virtualization controller and data transfer control method |
US7373670B2 (en) | 2003-11-26 | 2008-05-13 | Hitachi, Ltd. | Method and apparatus for setting access restriction information |
US7395396B2 (en) | 2004-08-30 | 2008-07-01 | Hitachi, Ltd. | Storage system and data relocation control device |
US7500134B2 (en) | 2005-12-27 | 2009-03-03 | Emc Corporation | Virtual array failover |
US7673107B2 (en) | 2004-10-27 | 2010-03-02 | Hitachi, Ltd. | Storage system and storage control device |
US7685395B1 (en) | 2005-12-27 | 2010-03-23 | Emc Corporation | Spanning virtual arrays across multiple physical storage arrays |
US7697554B1 (en) | 2005-12-27 | 2010-04-13 | Emc Corporation | On-line data migration of a logical/virtual storage array by replacing virtual names |
US7707377B2 (en) | 2003-09-17 | 2010-04-27 | Hitachi, Ltd. | Remote storage disk control device and method for controlling the same |
US7757059B1 (en) | 2006-06-29 | 2010-07-13 | Emc Corporation | Virtual array non-disruptive management data migration |
US7809906B2 (en) | 2004-02-26 | 2010-10-05 | Hitachi, Ltd. | Device for performance tuning in a system |
US7937513B2 (en) | 2002-04-26 | 2011-05-03 | Hitachi, Ltd. | Method for controlling storage system, and storage control apparatus |
US8072987B1 (en) | 2005-09-30 | 2011-12-06 | Emc Corporation | Full array non-disruptive data migration |
US8107467B1 (en) | 2005-09-30 | 2012-01-31 | Emc Corporation | Full array non-disruptive failover |
WO2012032576A1 (en) * | 2010-09-09 | 2012-03-15 | Hitachi, Ltd. | Computer system control method and computer system |
US8452928B1 (en) | 2006-06-29 | 2013-05-28 | Emc Corporation | Virtual array non-disruptive migration of extended storage functionality |
US8533408B1 (en) | 2006-06-29 | 2013-09-10 | Emc Corporation | Consolidating N-storage arrays into one storage array using virtual array non-disruptive data migration |
US8539177B1 (en) | 2006-06-29 | 2013-09-17 | Emc Corporation | Partitioning of a storage array into N-storage arrays using virtual array non-disruptive data migration |
US8583861B1 (en) | 2006-06-29 | 2013-11-12 | Emc Corporation | Presentation of management functionality of virtual arrays |
US8589504B1 (en) * | 2006-06-29 | 2013-11-19 | Emc Corporation | Full array non-disruptive management data migration |
CN103441988A (en) * | 2013-08-02 | 2013-12-11 | 广东电网公司电力科学研究院 | Data migration method crossing GIS platforms |
US9063896B1 (en) | 2007-06-29 | 2015-06-23 | Emc Corporation | System and method of non-disruptive data migration between virtual arrays of heterogeneous storage arrays |
US9063895B1 (en) | 2007-06-29 | 2015-06-23 | Emc Corporation | System and method of non-disruptive data migration between heterogeneous storage arrays |
US9098211B1 (en) | 2007-06-29 | 2015-08-04 | Emc Corporation | System and method of non-disruptive data migration between a full storage array and one or more virtual arrays |
US9207873B2 (en) | 2013-12-19 | 2015-12-08 | Netapp, Inc. | Parallel migration of data objects to clustered storage |
US9348530B2 (en) | 2005-12-27 | 2016-05-24 | Emc Corporation | Presentation of virtual arrays using n-port ID virtualization |
CN109196483A (en) * | 2016-07-27 | 2019-01-11 | 株式会社日立制作所 | Computer system and data save method |
CN113904971A (en) * | 2021-09-14 | 2022-01-07 | 中国电信集团系统集成有限责任公司 | Method for automatically exchanging routing information across network planes |
Families Citing this family (56)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3992427B2 (en) * | 2000-08-01 | 2007-10-17 | 株式会社日立製作所 | File system |
US7292528B2 (en) * | 2001-06-04 | 2007-11-06 | Turin Networks | Method and apparatus to facilitate independent protection switching in a distributed network |
US6898202B2 (en) * | 2001-06-27 | 2005-05-24 | International Business Machines Corporation | Method, apparatus and computer program for informing a requesting device of port configuration changes in a computer network switching device |
JP4026703B2 (en) | 2001-11-28 | 2007-12-26 | 株式会社日立製作所 | Storage device operation management system and operation management method |
US20030189929A1 (en) * | 2002-04-04 | 2003-10-09 | Fujitsu Limited | Electronic apparatus for assisting realization of storage area network system |
JP2003330762A (en) * | 2002-05-09 | 2003-11-21 | Hitachi Ltd | Control method for storage system, storage system, switch and program |
JP2004013215A (en) * | 2002-06-03 | 2004-01-15 | Hitachi Ltd | Storage system, storage sub-system, and information processing system including them |
JP2004102374A (en) * | 2002-09-05 | 2004-04-02 | Hitachi Ltd | Information processing system having data transition device |
JP2004110367A (en) | 2002-09-18 | 2004-04-08 | Hitachi Ltd | Storage system control method, storage control device, and storage system |
JP4325843B2 (en) * | 2002-12-20 | 2009-09-02 | 株式会社日立製作所 | Logical volume copy destination performance adjustment method and apparatus |
JP2004220450A (en) | 2003-01-16 | 2004-08-05 | Hitachi Ltd | Storage device, its introduction method and its introduction program |
JP2005018193A (en) | 2003-06-24 | 2005-01-20 | Hitachi Ltd | Interface command control method for disk device, and computer system |
JP4386694B2 (en) | 2003-09-16 | 2009-12-16 | 株式会社日立製作所 | Storage system and storage control device |
US7100002B2 (en) * | 2003-09-16 | 2006-08-29 | Denali Software, Inc. | Port independent data transaction interface for multi-port devices |
JP4307202B2 (en) | 2003-09-29 | 2009-08-05 | 株式会社日立製作所 | Storage system and storage control device |
JP4320247B2 (en) | 2003-12-24 | 2009-08-26 | 株式会社日立製作所 | Configuration information setting method and apparatus |
JP2005202893A (en) | 2004-01-19 | 2005-07-28 | Hitachi Ltd | Storage device controller, storage system, recording medium recording program, information processor, and method for controlling storage system |
JP2005222429A (en) * | 2004-02-09 | 2005-08-18 | Hitachi Ltd | Method for managing different types of disk devices in disk array apparatus |
US7039662B2 (en) * | 2004-02-24 | 2006-05-02 | Hitachi, Ltd. | Method and apparatus of media management on disk-subsystem |
US7924826B1 (en) * | 2004-05-03 | 2011-04-12 | Cisco Technology, Inc. | Method and apparatus for device pinout mapping |
JP4718851B2 (en) * | 2004-05-10 | 2011-07-06 | 株式会社日立製作所 | Data migration in storage systems |
JP4421999B2 (en) * | 2004-08-03 | 2010-02-24 | 株式会社日立製作所 | Storage apparatus, storage system, and data migration method for executing data migration with WORM function |
JP4504762B2 (en) * | 2004-08-19 | 2010-07-14 | 株式会社日立製作所 | Storage network migration method, management apparatus, management program, and storage network system |
JP4646574B2 (en) | 2004-08-30 | 2011-03-09 | 株式会社日立製作所 | Data processing system |
JP2006127201A (en) * | 2004-10-29 | 2006-05-18 | Hitachi Ltd | Storage system and conduction confirmation method |
JP4585276B2 (en) | 2004-11-01 | 2010-11-24 | 株式会社日立製作所 | Storage system |
US7590780B2 (en) * | 2004-11-08 | 2009-09-15 | Broadcom Corporation | Method and computer program product to migrate legacy data to a RAID array while contemporaneously providing user access to legacy data |
JP4741304B2 (en) * | 2005-07-11 | 2011-08-03 | 株式会社日立製作所 | Data migration method or data migration system |
JP4701929B2 (en) | 2005-09-02 | 2011-06-15 | 株式会社日立製作所 | Boot configuration change method, management server, and computer system |
JP2007140887A (en) * | 2005-11-18 | 2007-06-07 | Hitachi Ltd | Storage system, disk array device, method of presenting volume, and method of verifying data consistency |
JP5057741B2 (en) * | 2006-10-12 | 2012-10-24 | 株式会社日立製作所 | Storage device |
JP5034495B2 (en) | 2006-12-27 | 2012-09-26 | 日本電気株式会社 | Storage system, program and method |
JP5022740B2 (en) * | 2007-03-09 | 2012-09-12 | 矢崎総業株式会社 | Relay connector unit, wire harness assembly, and electronic device control system |
JP5149556B2 (en) * | 2007-07-30 | 2013-02-20 | 株式会社日立製作所 | Storage system that migrates system information elements |
JP2009146106A (en) | 2007-12-13 | 2009-07-02 | Hitachi Ltd | Storage system having function which migrates virtual communication port which is added to physical communication port |
US9417812B1 (en) * | 2007-12-26 | 2016-08-16 | Emc Corporation | Methods and apparatus for minimally disruptive data migration |
US8341251B2 (en) * | 2008-01-03 | 2012-12-25 | International Business Machines Corporation | Enabling storage area network component migration |
WO2009093280A1 (en) * | 2008-01-21 | 2009-07-30 | Fujitsu Limited | Storage device |
US8914540B1 (en) * | 2008-07-01 | 2014-12-16 | Cisco Technology, Inc. | Multi-fabric SAN based data migration |
JP2010231567A (en) * | 2009-03-27 | 2010-10-14 | Fujitsu Ltd | Storage switch and method for changing storage area size |
WO2012017493A1 (en) * | 2010-08-06 | 2012-02-09 | 株式会社日立製作所 | Computer system and data migration method |
US20120054264A1 (en) | 2010-08-31 | 2012-03-01 | International Business Machines Corporation | Techniques for Migrating Active I/O Connections with Migrating Servers and Clients |
US8898333B1 (en) | 2010-08-31 | 2014-11-25 | Juniper Networks, Inc. | Methods and apparatus related to a virtual multi-hop network topology emulated within a data center |
US8797897B1 (en) | 2011-09-30 | 2014-08-05 | Juniper Networks, Inc. | Methods and apparatus with virtual identifiers for physical switches in a virtual chassis |
US9075811B2 (en) * | 2011-09-30 | 2015-07-07 | Symantec Corporation | Cloud information migration systems and methods |
US9063937B2 (en) | 2012-07-31 | 2015-06-23 | Hewlett-Packard Development Company, L.P. | Storage array reservation forwarding |
JP5423855B2 (en) * | 2012-09-18 | 2014-02-19 | 株式会社日立製作所 | How to change the boot configuration |
JP5501504B2 (en) * | 2013-04-01 | 2014-05-21 | 株式会社日立製作所 | Data migration control method for storage device |
US9779003B2 (en) | 2013-06-12 | 2017-10-03 | International Business Machines Corporation | Safely mapping and unmapping host SCSI volumes |
US9940019B2 (en) | 2013-06-12 | 2018-04-10 | International Business Machines Corporation | Online migration of a logical volume between storage systems |
US9769062B2 (en) | 2013-06-12 | 2017-09-19 | International Business Machines Corporation | Load balancing input/output operations between two computers |
US9274916B2 (en) | 2013-06-12 | 2016-03-01 | International Business Machines Corporation | Unit attention processing in proxy and owner storage systems |
US8819317B1 (en) | 2013-06-12 | 2014-08-26 | International Business Machines Corporation | Processing input/output requests using proxy and owner storage systems |
US9274989B2 (en) | 2013-06-12 | 2016-03-01 | International Business Machines Corporation | Impersonating SCSI ports through an intermediate proxy |
US9626125B2 (en) * | 2013-07-31 | 2017-04-18 | International Business Machines Corporation | Accounting for data that needs to be rebuilt or deleted |
WO2015162674A1 (en) * | 2014-04-21 | 2015-10-29 | 株式会社日立製作所 | Storage system |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5680640A (en) | 1995-09-01 | 1997-10-21 | Emc Corporation | System for migrating data by selecting a first or second transfer means based on the status of a data element map initialized to a predetermined state |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5544347A (en) * | 1990-09-24 | 1996-08-06 | Emc Corporation | Data storage system controlled remote data mirroring with respectively maintained data indices |
US5898828A (en) * | 1995-12-29 | 1999-04-27 | Emc Corporation | Reduction of power used by transceivers in a data transmission loop |
US6044444A (en) * | 1996-05-28 | 2000-03-28 | Emc Corporation | Remote data mirroring having preselection of automatic recovery or intervention required when a disruption is detected |
US6052797A (en) * | 1996-05-28 | 2000-04-18 | Emc Corporation | Remotely mirrored data storage system with a count indicative of data consistency |
JP3390608B2 (en) * | 1996-08-28 | 2003-03-24 | 株式会社日立製作所 | Storage network control method |
US6338110B1 (en) * | 1997-11-14 | 2002-01-08 | Sun Microsystems, Inc. | Partitioning of storage channels using programmable switches |
US6145066A (en) * | 1997-11-14 | 2000-11-07 | Amdahl Corporation | Computer system with transparent data migration between storage volumes |
US6654830B1 (en) * | 1999-03-25 | 2003-11-25 | Dell Products L.P. | Method and system for managing data migration for a storage system |
US6553408B1 (en) * | 1999-03-25 | 2003-04-22 | Dell Products L.P. | Virtual device architecture having memory for storing lists of driver modules |
-
2000
- 2000-03-03 JP JP2000063289A patent/JP3918394B2/en not_active Expired - Fee Related
- 2000-08-23 US US09/644,064 patent/US6976103B1/en not_active Expired - Fee Related
- 2000-09-14 EP EP00119434A patent/EP1130514A3/en not_active Withdrawn
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5680640A (en) | 1995-09-01 | 1997-10-21 | Emc Corporation | System for migrating data by selecting a first or second transfer means based on the status of a data element map initialized to a predetermined state |
Cited By (64)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7120673B2 (en) | 2000-05-18 | 2006-10-10 | Hitachi, Ltd. | Computer storage system providing virtualized storage |
EP1310876A1 (en) * | 2000-05-18 | 2003-05-14 | Hitachi, Ltd. | Computer system |
US6708232B2 (en) | 2000-06-29 | 2004-03-16 | Hitachi, Ltd. | Data migration method, protocol converter and switching apparatus using it |
US7130954B2 (en) | 2000-06-29 | 2006-10-31 | Hitachi, Ltd. | Data migration method, protocol converter and switching apparatus using it |
EP1589412A2 (en) * | 2001-11-13 | 2005-10-26 | Hitachi, Ltd. | Computer data migration system |
EP1589412A3 (en) * | 2001-11-13 | 2008-12-31 | Hitachi, Ltd. | Computer data migration system |
EP1347366A2 (en) * | 2002-03-20 | 2003-09-24 | Hitachi, Ltd. | Storage system, disk control cluster, and a method for increasing the number of disk control clusters in a storage system |
EP1347366A3 (en) * | 2002-03-20 | 2006-02-15 | Hitachi, Ltd. | Storage system, disk control cluster, and a method for increasing the number of disk control clusters in a storage system |
US7747827B2 (en) | 2002-03-20 | 2010-06-29 | Hitachi, Ltd. | Storage system, disk control cluster, and its increase method |
US7937513B2 (en) | 2002-04-26 | 2011-05-03 | Hitachi, Ltd. | Method for controlling storage system, and storage control apparatus |
US7877568B2 (en) | 2002-11-25 | 2011-01-25 | Hitachi, Ltd. | Virtualization controller and data transfer control method |
US8190852B2 (en) * | 2002-11-25 | 2012-05-29 | Hitachi, Ltd. | Virtualization controller and data transfer control method |
US7366853B2 (en) * | 2002-11-25 | 2008-04-29 | Hitachi, Ltd. | Virtualization controller and data transfer control method |
US8572352B2 (en) | 2002-11-25 | 2013-10-29 | Hitachi, Ltd. | Virtualization controller and data transfer control method |
US7694104B2 (en) | 2002-11-25 | 2010-04-06 | Hitachi, Ltd. | Virtualization controller and data transfer control method |
US7975116B2 (en) | 2003-09-17 | 2011-07-05 | Hitachi, Ltd. | Remote storage disk control device and method for controlling the same |
US8255652B2 (en) | 2003-09-17 | 2012-08-28 | Hitachi, Ltd. | Remote storage disk control device and method for controlling the same |
US7707377B2 (en) | 2003-09-17 | 2010-04-27 | Hitachi, Ltd. | Remote storage disk control device and method for controlling the same |
US7373670B2 (en) | 2003-11-26 | 2008-05-13 | Hitachi, Ltd. | Method and apparatus for setting access restriction information |
US8806657B2 (en) | 2003-11-26 | 2014-08-12 | Hitachi, Ltd. | Method and apparatus for setting access restriction information |
US8156561B2 (en) | 2003-11-26 | 2012-04-10 | Hitachi, Ltd. | Method and apparatus for setting access restriction information |
US7809906B2 (en) | 2004-02-26 | 2010-10-05 | Hitachi, Ltd. | Device for performance tuning in a system |
EP1569115A3 (en) * | 2004-02-26 | 2009-01-21 | Hitachi, Ltd. | Data migration method and apparatus |
EP1569115A2 (en) | 2004-02-26 | 2005-08-31 | Hitachi, Ltd. | Data migration method and apparatus |
US8281098B2 (en) | 2004-02-26 | 2012-10-02 | Hitachi, Ltd. | Storage subsystem and performance tuning method |
US8046554B2 (en) | 2004-02-26 | 2011-10-25 | Hitachi, Ltd. | Storage subsystem and performance tuning method |
US8230038B2 (en) | 2004-08-30 | 2012-07-24 | Hitachi, Ltd. | Storage system and data relocation control device |
US7395396B2 (en) | 2004-08-30 | 2008-07-01 | Hitachi, Ltd. | Storage system and data relocation control device |
US8799600B2 (en) | 2004-08-30 | 2014-08-05 | Hitachi, Ltd. | Storage system and data relocation control device |
US7424585B2 (en) | 2004-08-30 | 2008-09-09 | Hitachi, Ltd. | Storage system and data relocation control device |
US7096338B2 (en) | 2004-08-30 | 2006-08-22 | Hitachi, Ltd. | Storage system and data relocation control device |
US7673107B2 (en) | 2004-10-27 | 2010-03-02 | Hitachi, Ltd. | Storage system and storage control device |
US7343467B2 (en) | 2004-12-20 | 2008-03-11 | Emc Corporation | Method to perform parallel data migration in a clustered storage environment |
WO2006069178A2 (en) * | 2004-12-20 | 2006-06-29 | Emc Corporation | A method to perform parallel data migration in a clustered storage environment |
US7913056B2 (en) | 2004-12-20 | 2011-03-22 | Emc Corporation | Method to perform parallel data migration in a clustered storage environment |
WO2006069178A3 (en) * | 2004-12-20 | 2006-09-21 | Emc Corp | A method to perform parallel data migration in a clustered storage environment |
WO2006099826A3 (en) * | 2005-03-23 | 2007-01-11 | Fujitsu Siemens Computers Gmbh | Method for removing a mass storage system from a computer network, and computer program product and computer network for carrying out the method |
WO2006099826A2 (en) * | 2005-03-23 | 2006-09-28 | Fujitsu Siemens Computers Gmbh | Method for removing a mass storage system from a computer network, and computer program product and computer network for carrying out the method |
US8107467B1 (en) | 2005-09-30 | 2012-01-31 | Emc Corporation | Full array non-disruptive failover |
US8072987B1 (en) | 2005-09-30 | 2011-12-06 | Emc Corporation | Full array non-disruptive data migration |
US7500134B2 (en) | 2005-12-27 | 2009-03-03 | Emc Corporation | Virtual array failover |
US7697554B1 (en) | 2005-12-27 | 2010-04-13 | Emc Corporation | On-line data migration of a logical/virtual storage array by replacing virtual names |
US7697515B2 (en) | 2005-12-27 | 2010-04-13 | Emc Corporation | On-line data migration of a logical/virtual storage array |
US7685395B1 (en) | 2005-12-27 | 2010-03-23 | Emc Corporation | Spanning virtual arrays across multiple physical storage arrays |
US9348530B2 (en) | 2005-12-27 | 2016-05-24 | Emc Corporation | Presentation of virtual arrays using n-port ID virtualization |
WO2007076385A1 (en) * | 2005-12-27 | 2007-07-05 | Emc Corporation | On-line data migration of a logical/virtual storage array |
US8452928B1 (en) | 2006-06-29 | 2013-05-28 | Emc Corporation | Virtual array non-disruptive migration of extended storage functionality |
US7757059B1 (en) | 2006-06-29 | 2010-07-13 | Emc Corporation | Virtual array non-disruptive management data migration |
US8533408B1 (en) | 2006-06-29 | 2013-09-10 | Emc Corporation | Consolidating N-storage arrays into one storage array using virtual array non-disruptive data migration |
US8583861B1 (en) | 2006-06-29 | 2013-11-12 | Emc Corporation | Presentation of management functionality of virtual arrays |
US8589504B1 (en) * | 2006-06-29 | 2013-11-19 | Emc Corporation | Full array non-disruptive management data migration |
US8539177B1 (en) | 2006-06-29 | 2013-09-17 | Emc Corporation | Partitioning of a storage array into N-storage arrays using virtual array non-disruptive data migration |
US9063896B1 (en) | 2007-06-29 | 2015-06-23 | Emc Corporation | System and method of non-disruptive data migration between virtual arrays of heterogeneous storage arrays |
US9063895B1 (en) | 2007-06-29 | 2015-06-23 | Emc Corporation | System and method of non-disruptive data migration between heterogeneous storage arrays |
US9098211B1 (en) | 2007-06-29 | 2015-08-04 | Emc Corporation | System and method of non-disruptive data migration between a full storage array and one or more virtual arrays |
US8370588B2 (en) | 2010-09-09 | 2013-02-05 | Hitachi, Ltd. | Computer system control method and computer system |
WO2012032576A1 (en) * | 2010-09-09 | 2012-03-15 | Hitachi, Ltd. | Computer system control method and computer system |
CN103441988A (en) * | 2013-08-02 | 2013-12-11 | 广东电网公司电力科学研究院 | Data migration method crossing GIS platforms |
CN103441988B (en) * | 2013-08-02 | 2016-06-08 | 广东电网公司电力科学研究院 | Across GIS platform data migration method |
US9207873B2 (en) | 2013-12-19 | 2015-12-08 | Netapp, Inc. | Parallel migration of data objects to clustered storage |
US9503522B2 (en) | 2013-12-19 | 2016-11-22 | Netapp, Inc. | Parallel migration of data objects to clustered storage |
CN109196483A (en) * | 2016-07-27 | 2019-01-11 | 株式会社日立制作所 | Computer system and data save method |
CN109196483B (en) * | 2016-07-27 | 2023-04-21 | 株式会社日立制作所 | Computer system and data storage method |
CN113904971A (en) * | 2021-09-14 | 2022-01-07 | 中国电信集团系统集成有限责任公司 | Method for automatically exchanging routing information across network planes |
Also Published As
Publication number | Publication date |
---|---|
US6976103B1 (en) | 2005-12-13 |
JP3918394B2 (en) | 2007-05-23 |
EP1130514A3 (en) | 2007-12-05 |
JP2001249853A (en) | 2001-09-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6976103B1 (en) | Data migration method using storage area network | |
TWI734890B (en) | System and method for providing data replication in nvme-of ethernet ssd | |
JP4859471B2 (en) | Storage system and storage controller | |
JP4252301B2 (en) | Storage system and data backup method thereof | |
JP4500057B2 (en) | Data migration method | |
US9733868B2 (en) | Methods and apparatus for implementing exchange management for virtualization of storage within a storage area network | |
US6073209A (en) | Data storage controller providing multiple hosts with access to multiple storage subsystems | |
US8937965B2 (en) | Storage system comprising function for migrating virtual communication port added to physical communication port | |
JP4723873B2 (en) | Media management storage system | |
US7529816B2 (en) | System for providing multi-path input/output in a clustered data storage network | |
JP4014923B2 (en) | Shared memory control method and control system | |
US7904599B1 (en) | Synchronization and auditing of zone configuration data in storage-area networks | |
US20090327568A1 (en) | Data Replication method and apparatus | |
US20080183965A1 (en) | Controller for controlling a plurality of logical resources of a storage system | |
JP2000099272A (en) | Storage controller and handling method of data storage system using same | |
JP2006505831A (en) | Method and apparatus for realizing storage virtualization in a storage area network through a virtual enclosure | |
EP2146284B1 (en) | Remote copy system and method | |
US8949562B2 (en) | Storage system and method of controlling storage system | |
CN107704206B (en) | Method, device, equipment and storage medium for online migration of heterogeneous system data | |
US10229085B2 (en) | Fibre channel hardware card port assignment and management method for port names | |
US10782889B2 (en) | Fibre channel scale-out with physical path discovery and volume move | |
JP2007048323A (en) | Virtualization controller and data migration control method | |
US10798159B2 (en) | Methods for managing workload throughput in a storage system and devices thereof | |
EP1146695A2 (en) | Fibre channel service parameter cache |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
AK | Designated contracting states |
Kind code of ref document: A2 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE |
|
AX | Request for extension of the european patent |
Free format text: AL;LT;LV;MK;RO;SI |
|
PUAL | Search report despatched |
Free format text: ORIGINAL CODE: 0009013 |
|
AK | Designated contracting states |
Kind code of ref document: A3 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE |
|
AX | Request for extension of the european patent |
Extension state: AL LT LV MK RO SI |
|
RIC1 | Information provided on ipc code assigned before grant |
Ipc: G06F 11/14 20060101ALI20071031BHEP Ipc: G06F 3/06 20060101AFI20071031BHEP |
|
17P | Request for examination filed |
Effective date: 20080605 |
|
17Q | First examination report despatched |
Effective date: 20080711 |
|
AKX | Designation fees paid |
Designated state(s): DE FR GB |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
18D | Application deemed to be withdrawn |
Effective date: 20101020 |